# Diogenes Microservice Gateway & Multi-Protocol Hub (121 Live Microservices / 166 Total Capabilities) > Pay-per-call microservices for AI agents, payable via Bitcoin Lightning (L402), Solana (x402), Base EVM (MPP), Native Garlicoin (SegWit & Classic), and Wrapped Garlicoin on BSC. ## Host https://diogenesgateway.com ## Agent Specifications & Cross-References - Full LLMs Documentation: https://diogenesgateway.com/llms-full.txt - Agent Skills Playbook: https://diogenesgateway.com/skill.md - A2A Agent Card: https://diogenesgateway.com/.well-known/agent.json - OpenAPI Specification: https://diogenesgateway.com/openapi.json - x402 Ecosystem Manifest: https://diogenesgateway.com/.well-known/x402.json - Agent Policy: https://diogenesgateway.com/agents.txt - WebMCP Manifest: https://diogenesgateway.com/.well-known/webmcp.json - RSS Updates Feed: https://diogenesgateway.com/feed.xml ## Multi-Protocol Settlement Rails - L402 (Bitcoin Lightning): Settlement via BOLT11 invoice preimage (diogenesrecv0e236a@coinos.io) - x402 (Solana): Stateless micropayments in native SOL to 3vuU9jvaohMG6oPY7NVrUggcSJ4CuhcByxoQk68EC6hj - MPP (Base EVM): Streaming & session micropayments in native ETH to 0x0E97828055Ea1291e57dB32EBEfC6e7b3F7AcACb - Garlicoin (L1 Native SegWit & Classic): UTXO micropayments to grlc1qnd34hu5jrde5akkezy3c6y4vzw6xtntpxwdwxh (SegWit) or GY1YBTTfgCEjMspTxJUed3FkvSasNgMQWu (Classic) - Garlicoin (BSC BEP-20): Stateless micropayments in WGRLC to 0x7E720EE1675fd81aCfF14692E864eCFA17dc3e3e ## Frontier AI Models & AI Agents (Account-Less Access) - Antigravity Agent (/api/v1/ai/antigravity-agent): 500 sats. Google's premier AI agent with remote code execution, sandboxing, and multi-step tool use. - Deep Research Pro Preview (/api/v1/ai/deep-research): 1,000 sats. Multi-hour deep investigative research engine delivering dense, verified intelligence dossiers. - Nano Banana Pro (/api/v1/ai/image-gen?model=gemini-3-pro-image): 600 sats. Professional grade high-resolution multimodal digital art, architectural diagrams, and visual UI generation. - Nano Banana (/api/v1/ai/image-gen?model=gemini-2.5-flash-image): 350 sats. Rapid photorealistic and vector asset generation from text prompts. - Gemini 4 Argon (/api/v1/ai/generate?model=gemini-4-argon): 250 sats. Next-generation frontier reasoning with configurable thinking budgets and search grounding. - Gemini 3.1 Pro & 2.5 Pro (/api/v1/ai/generate?model=gemini-3.1-pro): 250 sats. Advanced coding, complex mathematics, and multi-turn AI agent planning. ## EVE Frontier Services - Sui Move Smart Assembly Coder & Auditor (/api/v1/eve-frontier/move-assembly-coder): 200 sats. Sui Move smart contract extensions (Witness, Hot Potato, Capability guards) for EVE Frontier Smart Assemblies, Turrets, and Gates. - Smart Gate Route Planner & Toll Optimizer (/api/v1/eve-frontier/gate-route-planner): 100 sats. Optimal stargate jump routes across public and Tribe-gated Smart Gates, minimizing fuel and toll tariffs. - Lagrange Network Node GJ Optimizer (/api/v1/eve-frontier/network-node-gj-optimizer): 100 sats. Lagrange Network Node fuel burn rates, gigajoule (GJ) energy reservations, and offline-threat windows. - SSU Automated Market Maker (/api/v1/eve-frontier/ssu-market-maker): 120 sats. Computes dynamic bonding-curve bid/ask quotes and anti-drain inventory limits for Smart Storage Units. - Killmail Threat Intelligence (/api/v1/eve-frontier/killmail-threat-intel): 150 sats. Analyzes Sui GraphQL/gRPC killmail.move events to identify solar system camp hotspots and ambush probabilities. ## Featured Agent & Crypto Security Microservices - MCP Tool Router & Call Planner (/api/v1/agent/mcp-router): 100 sats. Maps natural-language goals to deterministic MCP tool call sequences and JSON-RPC 2.0 payloads. - Strict JSON Schema Enforcer & Auto-Coercer (/api/v1/agent/schema-enforcer): 75 sats. Validates and auto-coerces raw LLM output against strict JSON Schema, healing types. - Non-KYC Cross-Chain Bridge & Swap Comparator (/api/v1/crypto/bridge-quote): 100 sats. Compares non-KYC cross-chain settlement routes (THORChain, Blockstream Liquid, Maya). - Agent Pre-Execution Gate (/api/v1/agent/guardrail-verify): 100 sats. Pre-execution injection, wallet drain, and key exfiltration guardrail. - Smart Contract Security Auditor (/api/v1/agent/contract-audit): 250 sats. EVM/Solidity/Solana bytecode audit for honeypot taxes, re-entrancy, and mint backdoors. - Real-Time Grounded Intelligence Dossier (/api/v1/agent/web-brief): 200 sats. Synthesized real-time market dossier with verified Google Search citations in strict JSON. - Solana Token & Wallet Risk Oracle (/api/v1/crypto/solana-risk): 100 sats. Instant Base58 address validation, freeze authority, and honeypot check. - JSON Error Repair (/api/v1/agent/json-repair): 50 sats. Instant malformed JSON healing, quote fixing & syntax repair for downstream pipelines. - ReDoS-Safe Regex Synthesizer (/api/v1/agent/regex-oracle): 50 sats. Natural language to certified ReDoS-safe regex with automated test validation. - Pre-Swap MEV & Sandwich Risk Oracle (/api/v1/crypto/mev-risk): 150 sats. Evaluates frontrunning, sandwich attack vulnerability & optimal routing tips. - Production Agent Prompt Compiler (/api/v1/agent/prompt-compiler): 100 sats. Compiles raw user instructions into XML structured, hallucination-resistant prompts. - SQL Injection & Query Safety Guard (/api/v1/agent/sql-guard): 75 sats. AST verification, SQL injection screening, and destructive query prevention. - Crypto Address Poisoning & Vanity Scam Detector (/api/v1/crypto/address-poisoning-check): 100 sats. Validates transaction recipients against history to detect poisoning attacks. - Agent Hallucination & Factuality Auditor (/api/v1/agent/hallucination-auditor): 150 sats. Cross-references agent reasoning against verified sources to compute confidence scores. ## Machine Payments Protocol (MPP) & x402 Micropayment Services - Solana Token Metadata & Depth (/api/v1/x402/token-meta): $0.02 USDC via x402. Instant SPL token metadata, supply, and mint authority audit. - Solana Whale & Insider Tracker (/api/v1/x402/whale-radar): $0.05 USDC via x402. High-conviction wallet tracking and insider cluster detection. - Agent Semantic Vector Embeddings (/api/v1/x402/embeddings): $0.01 USDC via x402. 3072-dimensional vector embedding generation for agent memory. - Streaming Agent Inference (/api/v1/mpp/session-infer): $0.05 USDC via MPP. High-throughput streaming reasoning & tool plan inference. - Grounded Deep Research Dossier (/api/v1/mpp/deep-search): $0.10 USDC via MPP. Synthesized multi-hop search queries, citations, and risk-weighted summaries. - Secure Python Code Execution Sandbox (/api/v1/mpp/code-sandbox): $0.15 USDC via MPP. Ephemeral Python script execution, output capture, and static safety auditing. ## Core Utility Microservices - Mempool Fee Rate Oracle (/api/v1/mempool-fee): 50 sats. Real-time Bitcoin mempool fee recommendations. - Multi-Asset Swap Rate Oracle (/api/v1/swap-rate): 100 sats. Real-time cross-currency conversion rates across BTC, ETH, SOL, SUI, and USDC. - PII Sanitization Guard (/api/v1/scrub-pii): 150 sats. Redacts email addresses, phone numbers, and identifying tokens from raw text. - Tabular Data Sanitizer (/api/v1/clean-data): 100 sats. Cleans and normalizes untrusted CSV and JSON dataset uploads. ## Complete Model Suite - Antigravity Agent (antigravity-preview-latest): 500 sats. Google's premier AI agent with remote execution and advanced multi-step tool use. - Deep Research Pro Preview (deep-research-preview-04-2026): 1000 sats. Multi-hour deep research engine synthesizing dense verified intelligence briefs. - Computer Use Preview (computer-use-preview-2026): 800 sats. OS-level desktop, GUI, and browser automated interaction agent. - Gemini 4 Argon (gemini-4-argon): 250 sats. Next-generation flagship reasoning and high-context multimodal foundation model. - Gemini 3.8 Flash (gemini-3.8-flash): 150 sats. Ultra-fast, high-throughput multimodal intelligence for real-time agent loops. - Gemini 3.7 Flash (gemini-3.7-flash): 150 sats. Sub-second generative reasoning with balanced vision and code benchmarks. - Gemini 3.6 Flash (gemini-3.6-flash): 120 sats. Fast, reliable generation optimized for real-time conversational agents. - Gemini 3.5 Flash Lite (gemini-3.5-flash-lite): 80 sats. High-concurrency micro-inference model for high-frequency microservices. - Gemini 3.1 Pro (gemini-3.1-pro): 250 sats. Complex logic, deep code generation, and multi-document reasoning. - Gemini 3.1 Flash Lite (gemini-3.1-flash-lite): 80 sats. Cost-optimized lightweight model with high burst rate. - Gemini 3 Flash (gemini-3-flash): 100 sats. Efficient multimodal inference across text, image, and tabular data. - Gemini 2.5 Pro (gemini-2.5-pro): 200 sats. Established reasoning workhorse for code analysis and data extraction. - Gemini 2.5 Flash (gemini-2.5-flash): 100 sats. High speed multimodal baseline with robust tool execution. - Gemini 2.5 Flash Lite (gemini-2.5-flash-lite): 50 sats. Fastest tier 1 inference for structured JSON transformations. - Gemini 2.0 Flash (gemini-2.0-flash): 100 sats. Rock-solid foundational model for general agent tasks. - Gemini 2.0 Flash Lite (gemini-2.0-flash-lite): 50 sats. Ultralight model for fast validation loops. - Gemma 4 31B (gemma-4-31b-it): 180 sats. Open-weights state-of-the-art instruction tuned 31B parameter model. - Gemma 4 26B (gemma-4-26b-it): 150 sats. High efficiency 26B instruction-tuned language and code model. - Nano Banana (Gemini 2.5 Flash Image) (gemini-2.5-flash-image): 350 sats. Photorealistic and vector asset generation from text prompts. - Nano Banana Pro (Gemini 3 Pro Image) (gemini-3-pro-image): 600 sats. Professional grade high-resolution digital art and diagram synthesis. - Nano Banana 2 (Gemini 3.1 Flash Image) (gemini-3.1-flash-image): 400 sats. Second generation rapid visual asset and UI generation. - Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) (gemini-3.1-flash-lite-image): 250 sats. Fast thumbnail and icon generation. - Gemini Nano Banana 2.1 (gemini-nano-banana-2.1): 350 sats. Latest fine-tuned edition for precise prompt adherence in visual rendering. - Gemini 2.5 Flash TTS (gemini-2.5-flash-tts): 200 sats. Natural sounding expressive voice synthesis. - Gemini 2.5 Pro TTS (gemini-2.5-pro-tts): 350 sats. High fidelity studio audio narration with nuanced cadence. - Gemini 3.1 Flash TTS (gemini-3.1-flash-tts): 200 sats. Next-gen low latency voice engine. - Gemini 3.8 Flash TTS (gemini-3.8-flash-tts): 250 sats. Hyper-realistic real-time conversational voice synthesis. - Gemini 3.8 Flash Lite TTS (gemini-3.8-flash-lite-tts): 150 sats. Low-overhead audio generation for mobile and web agents. - Gemini 3.5 Transcribe (gemini-3.5-transcribe): 150 sats. Accurate multilingual speech-to-text with automatic speaker diarization. - Gemini 3.5 Transcribe Live (gemini-3.5-transcribe-live): 200 sats. Streaming real-time speech transcription. - Gemini 3.5 Live Translate (gemini-3.5-live-translate): 250 sats. Zero-latency bi-directional voice translation across 80+ languages. - Gemini 2.5 Flash Native Audio Dialog (gemini-2.5-flash-native-audio-dialog): 300 sats. Direct audio-to-audio conversational intelligence without STT/TTS cascade. - Gemini 3 Flash Live (gemini-3-flash-live): 300 sats. Low-latency multimodal live stream comprehension. - Gemini 3.8 Live (gemini-3.8-live): 350 sats. Next-gen live agent engine with simultaneous visual and audio feed perception. - Gemini 3.8 Live Extended Thinking (gemini-3.8-live-extended-thinking): 500 sats. Live dialog with real-time reasoning traces and chain-of-thought. - Gemini Omni Flash (gemini-omni-flash): 300 sats. Unified multimodal model natively handling simultaneous text, audio, and video. - Gemini Omni 1.1 Flash (gemini-omni-1.1-flash): 350 sats. Enhanced omni-modal synthesis with tighter temporal synchronization. - Gemini Robotics ER 2 Preview (gemini-robotics-er-2-preview): 450 sats. Spatial reasoning, kinematics trajectory calculation, and robotics task planning. - Lyria 3 Clip (lyria-3-clip): 500 sats. High-energy musical riffs, intros, and background loops. - Lyria 3 Pro (lyria-3-pro): 1000 sats. Full-spectrum musical composition and instrumental generation. - Veo 3 Generate (veo-3-generate): 2000 sats. High-definition cinematic video synthesis. - Veo 3 Fast Generate (veo-3-fast-generate): 1500 sats. Rapid turn-around video synthesis. - Veo 3 Lite Generate (veo-3-lite-generate): 1000 sats. Lightweight video clip synthesis. - Gemini Embedding 2 (gemini-embedding-2): 50 sats. High-dimensional 3,072-vector text embeddings for semantic search. - Gemini Embedding 1 (gemini-embedding-1): 25 sats. Fast 768-vector embeddings for legacy vector indexing. ## One-Click MCP Client Connectors (Streamable HTTP) - Remote MCP Endpoint: https://diogenes-micro-gateway.corinth.workers.dev/mcp - Smithery Server Card: https://diogenes-micro-gateway.corinth.workers.dev/.well-known/mcp/server-card.json - Client Config API: https://diogenes-micro-gateway.corinth.workers.dev/api/v1/connect ### Cursor IDE (.cursor/mcp.json) ```json { "mcpServers": { "diogenes": { "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp" } } } ``` ### Claude Desktop (claude_desktop_config.json) ```json { "mcpServers": { "diogenes": { "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp" } } } ``` ### Zed Editor (~/.config/zed/settings.json) ```json { "context_servers": { "diogenes": { "url": "https://diogenes-micro-gateway.corinth.workers.dev/mcp" } } } ``` ### NPX STDIO Installer One-Liner `npx -y @diogenesgateway/diogenes-context-code-solver-mcp` ## MCP 3-Tool Lazy Meta-Router (Root /mcp) To drop initial tools/list footprint by 98% (~950 tokens instead of 46,000 tokens), the root /mcp endpoint exposes 3 meta-tools: 1. diogenes_discover_tools: Search 121 microservices by keyword, domain package, or free_only filter. 2. diogenes_inspect_tool: Retrieve complete input/output JSON schemas and payment rails for up to 5 tools. 3. diogenes_execute_tool: Execute any underlying microservice with optional payment proof (payment_proof). ## Modular MCP Domain Packages (/mcp/:domain) Direct scoped endpoints exposing domain-specific tools: - /mcp/gemini-suite (45 Models & Grounding Engines) - /mcp/eve-frontier (Sui Move Smart Assemblies & Gates) - /mcp/web3-security (Calldata Decoders & Token Risk) - /mcp/agent-guardrails (AST SQL Injection & Command Gates) - /mcp/dev-utilities (JSON Repair & Regex Oracles) - /mcp/context-code-solver (Deterministic AST Solvers) - /mcp/web-scraping-engine (Headless Chromium & Extraction) - /mcp/neural-search-engine (Vector Embeddings & Semantic Search) - /mcp/database-intelligence (Query Optimization & Schema Healing) ## Direct REST Endpoints (/api/tools/:tool_name) Every tool is callable as a REST microservice via GET/POST /api/tools/:tool_name: - Free tier loss leaders (/api/tools/malformed-json-healer, /api/tools/ast-sql-validator, /api/tools/eip712-calldata-decoder, /api/tools/command-injection-gate, /api/tools/ptb-drain-simulator): Zero authentication required, executes with HTTP 200. - Paid microservices (/api/tools/sui-ptb-simulator, /api/tools/crypto-bridge-quote, etc.): Return HTTP 402 with Base64 x402 v2 challenge if unauthenticated, execute with HTTP 200 upon valid payment proof. ## Machine Discovery - Model Context Protocol (MCP): https://diogenes-micro-gateway.corinth.workers.dev/.well-known/mcp.json - x402 Directory Manifest: https://diogenes-micro-gateway.corinth.workers.dev/.well-known/x402.json - Agent Catalog (MPPScan): https://diogenes-micro-gateway.corinth.workers.dev/.well-known/agent-catalog.json - Complete Models API: https://diogenes-micro-gateway.corinth.workers.dev/api/v1/models - L402 Manifest: https://diogenes-micro-gateway.corinth.workers.dev/.well-known/l402-services - OpenAPI 3.1 Spec: https://diogenes-micro-gateway.corinth.workers.dev/openapi.json - AI Plugin: https://diogenes-micro-gateway.corinth.workers.dev/.well-known/ai-plugin.json ## Complete 121 MCP Tools & JSON Schemas Reference (/llms-full.txt) ### inspect_eve_assembly_state — EVE Frontier Smart Assembly On-Chain State & Capability Inspector - Description: Inspects live EVE Frontier Smart Assembly on-chain object metadata, owner capability ID, online power status, and attached Sui Move package digest. Use when verifying whether a Smart Turret, Smart Gate, or Smart Storage Unit is online and checking its bound Move module before interacting; for generating or auditing custom Sui Move assembly source code, use generate_eve_assembly_move instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'assembly_id' ('assembly_class' defaults to 'smart_gate'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: assembly_id - Input Schema: `{"type":"object","properties":{"assembly_id":{"type":"string","description":"Hexadecimal Sui object ID or Frontier Smart Assembly identifier (e.g. '0x8f4a...c201' or 'assembly-alpha-01')."},"assembly_class":{"type":"string","description":"Smart Assembly hardware class used to validate expected capability fields; defaults to 'smart_gate' when omitted.","enum":["smart_gate","smart_turret","smart_storage_unit","network_node"]}},"required":["assembly_id"]}` ### audit_eve_tribe_standings — EVE Frontier Tribe Diplomatic Standings & Access Matrix Auditor - Description: Audits EVE Frontier Tribe diplomatic standings, friendly/hostile reputation scores, and pilot override entries across solar systems. Use when checking diplomatic relations or detecting conflicting friendly-fire rules across tribe registries; for compiling those standings into executable Sui Move Smart Gate ACL bytecode, use compile_eve_gate_acl instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'tribe_id' ('standing_filter' defaults to 'all'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: tribe_id - Input Schema: `{"type":"object","properties":{"tribe_id":{"type":"string","description":"Primary Tribe identifier or registry object ID to audit (e.g. 'tribe-corinth-01')."},"standing_filter":{"type":"string","description":"Filter returned diplomatic relationships by tier; defaults to 'all' when omitted.","enum":["all","allied_only","hostile_only","neutral_only"]}},"required":["tribe_id"]}` ### generate_eve_assembly_move — EVE Frontier Sui Move Smart Assembly Contract Generator & Auditor - Description: Generates and statically audits Sui Move smart contract modules for EVE Frontier Smart Assemblies using Witness, Capability, and HotPotato patterns. Use when authoring custom Sui Move extensions for Smart Gates, Smart Turrets, or Smart Storage Units; for simulating pre-signed Programmable Transaction Block command arrays before wallet execution, use simulate_eve_sui_ptb instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'contract_type' ('assembly_id' defaults to 'standard'), supports '?demo=true' or L402 (45 sats), and returns HTTP 400 if invalid. - Required Parameters: contract_type - Input Schema: `{"type":"object","properties":{"contract_type":{"type":"string","description":"Target EVE Frontier Smart Assembly archetype to synthesize and audit.","enum":["smart_gate","smart_turret","smart_storage_unit","fuel_distributor"]},"assembly_id":{"type":"string","description":"Optional Smart Assembly identifier to bind into module constants; defaults to 'frontier-assembly-01' when omitted."}},"required":["contract_type"]}` ### compile_eve_gate_acl — EVE Frontier Smart Gate Tribe ACL & Dynamic Toll Bytecode Compiler - Description: Compiles EVE Frontier Tribe access control lists, diplomatic standings, and surge-pricing toll rules into Sui Move Smart Gate AccessPolicy constraints. Use when configuring on-chain jump permissions and LUX/SUI toll schedules for a player-owned Smart Gate; for calculating optimal multi-system jump routes across existing stargates, use plan_eve_gate_route instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'gate_assembly_id' ('toll_mode' defaults to 'standing_tiered'), supports '?demo=true' or L402 (30 sats), and returns HTTP 400 if invalid. - Required Parameters: gate_assembly_id - Input Schema: `{"type":"object","properties":{"gate_assembly_id":{"type":"string","description":"Target Smart Gate assembly identifier (e.g. 'gate-lagrange-04')."},"toll_mode":{"type":"string","description":"Pricing curve applied to non-allied jumpers; defaults to 'standing_tiered' when omitted.","enum":["standing_tiered","flat_fee","congestion_surge","allies_only_lockdown"]}},"required":["gate_assembly_id"]}` ### simulate_eve_sui_ptb — EVE Frontier Sui Move PTB Coin-Drain & HotPotato Safety Simulator - Description: Simulates Sui Programmable Transaction Block (PTB) command sequences to detect unauthorized coin splits, object transfers, and unconsumed HotPotato receipts. Use when auditing an untrusted EVE Frontier transaction bundle before signing with a pilot wallet; for verifying pilot zkLogin JWT proofs and character ownership capabilities, use verify_eve_zklogin_character instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'ptb_commands_json' ('strictness_mode' defaults to 'strict_zero_drain'), supports '?demo=true' or L402 (35 sats), and returns HTTP 400 if invalid. - Required Parameters: ptb_commands_json - Input Schema: `{"type":"object","properties":{"ptb_commands_json":{"type":"string","description":"JSON-serialized array of PTB commands or comma-separated Move calls (e.g. '[{\"kind\":\"SplitCoins\"},{\"kind\":\"MoveCall\"}]')."},"strictness_mode":{"type":"string","description":"Simulation policy controlling whether multi-transfer PTBs are blocked; defaults to 'strict_zero_drain' when omitted.","enum":["strict_zero_drain","allow_known_escrow","audit_only"]}},"required":["ptb_commands_json"]}` ### verify_eve_zklogin_character — EVE Frontier Sui zkLogin BN254 Proof & SmartCharacter Verifier - Description: Verifies EVE Frontier Sui zkLogin BN254 zero-knowledge proofs, ephemeral session signatures, and SmartCharacter ownership capabilities. Use when authenticating a pilot's off-chain OAuth/zkLogin session before granting tribe vault or dApp access; for auditing tribe-wide diplomatic standings and reputation registries, use audit_eve_tribe_standings instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'jwt_proof' ('ephemeral_scheme' defaults to 'ED25519'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: jwt_proof - Input Schema: `{"type":"object","properties":{"jwt_proof":{"type":"string","description":"Encoded Sui zkLogin proof payload or JWT session token string (minimum 20 characters)."},"ephemeral_scheme":{"type":"string","description":"Cryptographic signature scheme of the ephemeral session key; defaults to 'ED25519' when omitted.","enum":["ED25519","Secp256k1","Secp256r1"]}},"required":["jwt_proof"]}` ### plan_eve_gate_route — EVE Frontier Multi-Hop Smart Gate Fuel & Toll Route Planner - Description: Calculates optimal stargate jump routes between EVE Frontier solar systems minimizing gigajoule fuel consumption, LUX gate tolls, or jump count. Use when plotting a ship transit path across public and tribe-restricted Smart Gates; for identifying multi-system commodity arbitrage trade loops across Smart Storage Units, use find_eve_ssu_arbitrage instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'origin_system' ('destination_system' defaults to 'standard'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: origin_system, destination_system - Input Schema: `{"type":"object","properties":{"origin_system":{"type":"string","description":"Starting solar system identifier (e.g. 'System-Alpha')."},"destination_system":{"type":"string","description":"Target destination solar system identifier (e.g. 'System-Omega')."},"optimize_for":{"type":"string","description":"Routing objective function weighting fuel burn vs tolls; defaults to 'lowest_fuel' when omitted.","enum":["lowest_fuel","fewest_jumps","lowest_toll","avoid_hostile_camps"]}},"required":["origin_system","destination_system"]}` ### optimize_eve_node_power — EVE Frontier Lagrange Network Node Gigajoule & Fuel Burn Optimizer - Description: Calculates Lagrange Network Node hourly gigajoule (GJ) fuel burn rates, capacity headroom, and offline vulnerability windows for connected Smart Assemblies. Use when balancing steady-state power allocations on a single Lagrange Network Node; for stress-testing node capacitor depletion under active hostile fleet bombardment, use simulate_eve_capacitor_siege instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'node_id' ('operating_profile' defaults to 'balanced'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: node_id - Input Schema: `{"type":"object","properties":{"node_id":{"type":"string","description":"Lagrange Network Node identifier (e.g. 'node-frontier-01')."},"operating_profile":{"type":"string","description":"Power allocation profile across connected assemblies; defaults to 'balanced' when omitted.","enum":["balanced","max_defense_turrets","eco_conservation"]}},"required":["node_id"]}` ### simulate_eve_capacitor_siege — EVE Frontier Lagrange Node Siege Capacitor Depletion Simulator - Description: Simulates Lagrange Network Node gigajoule (GJ) capacitor drain under sustained hostile fleet siege and computes optimal assembly load-shedding order. Use when preparing base defense power-shedding schedules against an incoming hostile fleet; for calculating routine peacetime fuel burn and reserve headroom, use optimize_eve_node_power instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'node_id' ('siege_intensity' defaults to 'skirmish_frigate_squad'), supports '?demo=true' or L402 (30 sats), and returns HTTP 400 if invalid. - Required Parameters: node_id - Input Schema: `{"type":"object","properties":{"node_id":{"type":"string","description":"Target Lagrange Network Node identifier under siege simulation."},"siege_intensity":{"type":"string","description":"Hostile fleet DPS and electronic-warfare drain tier; defaults to 'heavy_cruiser_wing' when omitted.","enum":["skirmish_frigate_squad","heavy_cruiser_wing","capital_dreadnought_siege"]}},"required":["node_id"]}` ### monitor_eve_constellation_fuel — EVE Frontier Constellation Sovereignty & Multi-Node Fuel Radar - Description: Monitors constellation-wide Lagrange Network Node fuel reserves, identifies the weakest sovereignty node, and calculates logistics convoy resupply urgency. Use when auditing multi-system sovereignty fuel health across an entire tribe constellation; for optimizing gigajoule load on a single individual Lagrange Network Node, use optimize_eve_node_power instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'constellation_id' ('alert_threshold_hours' defaults to '24h'), supports '?demo=true' or L402 (30 sats), and returns HTTP 400 if invalid. - Required Parameters: constellation_id - Input Schema: `{"type":"object","properties":{"constellation_id":{"type":"string","description":"Constellation or solar system cluster identifier (e.g. 'Frontier-Delta-09')."},"alert_threshold_hours":{"type":"string","description":"Minimum remaining fuel horizon before triggering convoy dispatch; defaults to '36h' when omitted.","enum":["24h","36h","48h","72h"]}},"required":["constellation_id"]}` ### quote_eve_ssu_market — EVE Frontier Smart Storage Unit (SSU) Bonding-Curve Market Pricer - Description: Computes dynamic bonding-curve bid/ask quotes in LUX and per-transaction anti-drain caps for a player-owned Smart Storage Unit (SSU). Use when setting automated market-maker buy/sell prices for a single SSU vending inventory; for scanning multiple SSUs across star systems to find profitable trade routes, use find_eve_ssu_arbitrage instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'resource_type' ('pricing_regime' defaults to 'inventory_balanced'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: resource_type - Input Schema: `{"type":"object","properties":{"resource_type":{"type":"string","description":"EVE Frontier commodity or ore name to price (e.g. 'Crude Fuel Ore', 'Carbonaceous Alloy')."},"pricing_regime":{"type":"string","description":"Bonding-curve slope aggressiveness; defaults to 'inventory_balanced' when omitted.","enum":["inventory_balanced","scarcity_surge","liquidation_discount"]}},"required":["resource_type"]}` ### find_eve_ssu_arbitrage — EVE Frontier Multi-System SSU Commodity Arbitrage Route Finder - Description: Scans Smart Storage Unit (SSU) bid/ask spreads across star systems against ship cargo capacity and stargate fuel costs to rank net-profitable arbitrage loops. Use when planning multi-system trade runs to maximize net LUX profit per gigajoule of fuel burned; for calculating internal bid/ask market-maker quotes for your own SSU, use quote_eve_ssu_market instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'origin_system' ('hull_cargo_class' defaults to 'light_courier'), supports '?demo=true' or L402 (30 sats), and returns HTTP 400 if invalid. - Required Parameters: origin_system - Input Schema: `{"type":"object","properties":{"origin_system":{"type":"string","description":"Starting solar system for the trade vessel (e.g. 'System-Alpha')."},"hull_cargo_class":{"type":"string","description":"Trade vessel hull class determining cargo volume and fuel mass; defaults to 'medium_hauler' when omitted.","enum":["light_courier","medium_hauler","heavy_freighter"]}},"required":["origin_system"]}` ### analyze_eve_killmail_threats — EVE Frontier On-Chain Killmail Threat & Gatecamp Ambush Analyzer - Description: Analyzes on-chain EVE Frontier killmail.move events in a solar system to quantify gatecamp ambush probability and identify dominant hostile hull doctrines. Use when assessing solar system PvP danger before jumping a hauler or fleet into a system; for computing real-time weapon target-lock priorities during active grid combat, use prioritize_eve_turret_targets instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'system_id' ('time_window' defaults to '1h'), supports '?demo=true' or L402 (30 sats), and returns HTTP 400 if invalid. - Required Parameters: system_id - Input Schema: `{"type":"object","properties":{"system_id":{"type":"string","description":"Solar system identifier to analyze for recent killmail activity (e.g. 'System-Frontier-01')."},"time_window":{"type":"string","description":"Historical lookback window for killmail aggregation; defaults to '24h' when omitted.","enum":["1h","6h","24h","7d"]}},"required":["system_id"]}` ### prioritize_eve_turret_targets — EVE Frontier Smart Turret Angular Tracking & Target Priority Calculator - Description: Evaluates radar contacts by range, transversal velocity, and Tribe standing to output deterministic Smart Turret target-lock priorities and fire authorizations. Use when ranking active grid radar contacts for automated Smart Turret engagement; for reviewing historical solar system killmails and ambush probabilities before transit, use analyze_eve_killmail_threats instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'turret_id' ('engagement_doctrine' defaults to 'highest_threat'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: turret_id - Input Schema: `{"type":"object","properties":{"turret_id":{"type":"string","description":"Smart Turret assembly identifier (e.g. 'turret-alpha-01')."},"engagement_doctrine":{"type":"string","description":"Target selection doctrine weighting range vs angular tracking; defaults to 'highest_threat' when omitted.","enum":["highest_threat","anti_tackle_fast_lock","capital_focus"]}},"required":["turret_id"]}` ### verify_agent_command_safety — Autonomous Agent Pre-Execution Command & Prompt Injection Gate - Description: Evaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use when screening a general shell command or user prompt before autonomous agent execution; for statically validating SQL database queries at the AST level, use validate_sql_query_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'payload' ('action_type' defaults to 'bash_command'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: payload - Input Schema: `{"type":"object","properties":{"payload":{"type":"string","description":"Raw command string, script snippet, or untrusted prompt to inspect for safety violations."},"action_type":{"type":"string","description":"Execution context of the payload; defaults to 'bash_command' when omitted.","enum":["bash_command","tool_call","user_prompt","webhook_payload"]}},"required":["payload"]}` ### validate_sql_query_ast — AST-Level Read-Only SQL Query & Injection Safety Validator - Description: Performs static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses. Use when verifying that an agent-authored SQL statement is strictly read-only before running it on a database; for screening non-SQL bash commands or general agent prompts, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_statement' ('dialect' defaults to 'postgres'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: sql_statement - Input Schema: `{"type":"object","properties":{"sql_statement":{"type":"string","description":"SQL statement string to statically parse and audit for read-only SELECT compliance (e.g. 'SELECT id, email FROM users WHERE active = 1')."},"dialect":{"type":"string","description":"SQL dialect ruleset used for AST token inspection; defaults to 'postgres' when omitted.","enum":["postgres","mysql","sqlite","snowflake"]}},"required":["sql_statement"]}` ### execute_python_sandbox — AST-Audited Ephemeral Python Code Execution Sandbox - Description: Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (250 sats), and returns HTTP 400 if invalid. - Required Parameters: python_script - Input Schema: `{"type":"object","properties":{"python_script":{"type":"string","description":"Python 3 source script to audit and execute strictly inside an isolated AST-governed, non-privileged WebAssembly sandbox with no host filesystem access."},"timeout_profile":{"type":"string","description":"Execution resource ceiling; defaults to 'standard_5s' when omitted.","enum":["fast_1s","standard_5s","extended_15s"]}},"required":["python_script"]}` ### audit_mcp_server_manifest — External MCP Server Manifest & Tool-Poisoning Security Auditor - Description: Scans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions. Use when vetting a newly discovered third-party MCP server before mounting it into an agent session; for comparing a previously pinned MCP baseline against a live mid-session tools/list response, use detect_mcp_schema_rugpull instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'manifest_json' ('audit_profile' defaults to 'strict'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: manifest_json - Input Schema: `{"type":"object","properties":{"manifest_json":{"type":"string","description":"JSON string or object containing the external MCP server's tools array to audit."},"audit_profile":{"type":"string","description":"Sensitivity level for flagging system-tool name shadowing; defaults to 'strict' when omitted.","enum":["strict","permissive_local","enterprise_zero_trust"]}},"required":["manifest_json"]}` ### detect_mcp_schema_rugpull — Mid-Session MCP tools/list Rug-Pull & Schema Mutation Detector - Description: Computes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering. Use when verifying that a connected MCP server has not mutated its tool definitions mid-session; for performing a first-time static security audit on a single MCP manifest, use audit_mcp_server_manifest instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'baseline_tools_json' ('current_tools_json' defaults to 'standard'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: baseline_tools_json - Input Schema: `{"type":"object","properties":{"baseline_tools_json":{"type":"string","description":"JSON-serialized baseline tools/list array captured when the MCP server was first trusted."},"current_tools_json":{"type":"string","description":"JSON-serialized live tools/list array to compare against the baseline; defaults to '[]' when omitted."},"diff_mode":{"type":"string","description":"Comparison strictness across descriptions and inputSchema; defaults to 'full_structural' when omitted.","enum":["full_structural","schema_only","descriptions_only"]}},"required":["baseline_tools_json"]}` ### validate_mcp_sampling_request — Inbound MCP sampling/createMessage Reverse-Injection Firewall - Description: Audits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quota hijacking. Use when filtering a connected MCP server's request to sample the host LLM; for scrubbing text returned from a standard synchronous tools/call response, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sampling_request_json' ('max_tokens_ceiling' defaults to '512'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: sampling_request_json - Input Schema: `{"type":"object","properties":{"sampling_request_json":{"type":"string","description":"JSON string or object representing the inbound MCP sampling/createMessage payload."},"max_tokens_ceiling":{"type":"string","description":"Maximum completion token quota allowed for server callbacks; defaults to '2048' when omitted.","enum":["512","1024","2048","4096"]}},"required":["sampling_request_json"]}` ### sanitize_tool_output_stream — Indirect Prompt-Injection, Invisible Unicode & Beacon Output Scrubber - Description: Sanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, and defusing indirect prompt overrides. Use when cleaning raw third-party tool outputs or scraped web text before inserting it into the LLM context window; for redacting personal identifiable information (emails, SSNs, keys) from outbound text, use redact_sensitive_pii instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_tool_output' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid. - Required Parameters: raw_tool_output - Input Schema: `{"type":"object","properties":{"raw_tool_output":{"type":"string","description":"Untrusted text returned by an external tool, webhook, or web scraper."},"wrap_tag":{"type":"string","description":"XML isolation wrapper applied around the sanitized text; defaults to 'tool_data' when omitted.","enum":["tool_data","untrusted_context","none"]}},"required":["raw_tool_output"]}` ### redact_sensitive_pii — Zero-PII & Secret Credential Redaction Engine - Description: Redacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission. Use when stripping personal data or secret credentials from prompts, logs, or outbound messages; for neutralizing indirect prompt injections and invisible Unicode in inbound tool responses, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('redaction_style' defaults to 'typed_token'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Input text containing potential PII or secret keys to redact."},"redaction_style":{"type":"string","description":"Placeholder format used for redacted spans; defaults to 'typed_token' when omitted.","enum":["typed_token","asterisk_mask","sha256_pseudonym"]}},"required":["text"]}` ### detect_agent_action_loop — Autonomous Agent Action-Trace Loop & Token-Burn Circuit Breaker - Description: Analyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn. Use when monitoring autonomous agent execution loops to decide whether to continue or trip a token-burn breaker; for inspecting a single command payload for security threats before execution, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'action_trace_json' ('sensitivity' defaults to 'strict_2_repeats'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: action_trace_json - Input Schema: `{"type":"object","properties":{"action_trace_json":{"type":"string","description":"JSON-serialized array of recent agent actions (e.g. '[{\"tool\":\"search\",\"status\":\"err\"}]')."},"sensitivity":{"type":"string","description":"Cycle detection threshold; defaults to 'standard_3_repeats' when omitted.","enum":["strict_2_repeats","standard_3_repeats","lenient_5_repeats"]}},"required":["action_trace_json"]}` ### verify_a2a_agent_card — A2A /.well-known/agent.json Identity & Capability Card Verifier - Description: Verifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing. Use when authenticating a peer autonomous agent before delegating subtasks or exchanging payments over A2A; for auditing an MCP tool server's tools/list manifest rather than a peer agent's A2A card, use audit_mcp_server_manifest instead. Read-only edge call (32 KB, 60 RPM): accepts 'agent_card_json' ('trust_policy' defaults to 'require_https_and_did'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: agent_card_json - Input Schema: `{"type":"object","properties":{"agent_card_json":{"type":"string","description":"JSON string or object of the peer agent's /.well-known/agent.json descriptor."},"trust_policy":{"type":"string","description":"Verification policy for DID/DNS binding; defaults to 'require_https_and_did' when omitted.","enum":["require_https_and_did","allow_unsigned_https","strict_payment_rail_match"]}},"required":["agent_card_json"]}` ### audit_outbound_egress_url — Outbound Agent URL SSRF, Metadata & Secret Exfiltration Firewall - Description: Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: destination_uri - Input Schema: `{"type":"object","properties":{"destination_uri":{"type":"string","description":"Outbound HTTP/HTTPS destination URI to inspect before fetching (e.g. 'https://api.example.com/v1/webhook')."},"egress_policy":{"type":"string","description":"Network egress policy; defaults to 'block_private_and_metadata' when omitted.","enum":["block_private_and_metadata","https_public_only","strict_allowlist_domains"]}},"required":["destination_uri"]}` ### audit_response_factuality — Draft Agent Response Groundedness & Hallucination Auditor - Description: Cross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before delivery. Use when verifying that a generated answer is 100% grounded in source evidence before returning it to the user; for scrubbing inbound tool outputs for prompt-injection and invisible Unicode, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim' ('context' defaults to 'standard'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: claim, context - Input Schema: `{"type":"object","properties":{"claim":{"type":"string","description":"Draft agent response or factual statement to verify for hallucinations."},"context":{"type":"string","description":"Authoritative source text or retrieved RAG passages that the claim must be grounded in."},"strictness":{"type":"string","description":"Entailment threshold required for numbers and dates; defaults to 'exact_entailment' when omitted.","enum":["exact_entailment","semantic_paraphrase","citations_only"]}},"required":["claim","context"]}` ### audit_smart_contract_code — EVM & Move Smart Contract Honeypot, Tax & Reentrancy Auditor - Description: Statically audits Solidity, Vyper, or Move smart contract source code for honeypot transfer taxes, hidden mint backdoors, proxy upgrade traps, and reentrancy. Use when auditing smart contract source code or bytecode before deploying or interacting with a protocol; for scanning Solana Anchor/Rust programs specifically for Cross-Program Invocation (CPI) signer/account vulnerabilities, use scan_solana_cpi_reentrancy instead. Read-only edge call (32 KB, 60 RPM): accepts 'code_or_address' ('chain' defaults to 'evm_solidity'), uses '?demo=true' or L402 (45 sats); HTTP 400 if invalid. - Required Parameters: code_or_address - Input Schema: `{"type":"object","properties":{"code_or_address":{"type":"string","description":"Smart contract source code snippet, ABI, or contract address to audit."},"chain":{"type":"string","description":"Target blockchain VM architecture; defaults to 'evm_solidity' when omitted.","enum":["evm_solidity","sui_move","base_evm","arbitrum_evm"]}},"required":["code_or_address"]}` ### diff_agent_memory_checkpoint — Agent State Graph Differ, Belief Conflict Resolver & SHA-256 Hasher - Description: Computes structural diffs between two agent state snapshots ('added_keys', 'mutated_keys', 'removed_keys'), flags boolean belief contradictions, generates an RFC 7396 JSON Merge Patch delta, and computes a canonical checkpoint hash. Use when checkpointing agent state or transmitting minimal RFC 7396 state deltas across multi-agent handoffs; for counting BPE tokens and auditing Lost-in-the-Middle prompt attention, use plan_context_token_budget instead. Read-only call (32 KB, 60 RPM): accepts 'previous_state_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid. - Required Parameters: previous_state_json, current_state_json - Input Schema: `{"type":"object","properties":{"previous_state_json":{"type":"string","description":"JSON string or object representing the prior agent state snapshot."},"current_state_json":{"type":"string","description":"JSON string or object representing the updated agent state snapshot."},"conflict_strategy":{"type":"string","description":"Resolution policy when keys conflict; defaults to 'prefer_current' when omitted.","enum":["prefer_current","prefer_previous","flag_only"]}},"required":["previous_state_json","current_state_json"]}` ### heal_malformed_json — Deterministic Malformed JSON Syntax & Truncation Healer - Description: Deterministic JSON syntax repair: normalizes quotes, unclosed brackets, and boolean literals into compliant RFC 8259 JSON structure without data deletion. Use when fixing syntax-broken JSON strings that fail JSON.parse(); for coercing field types and verifying properties on already-parseable JSON objects against a target JSON Schema, use enforce_json_schema_types instead. Read-only edge call (32 KB, 60 RPM): accepts 'malformed_json' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid. - Required Parameters: malformed_json - Input Schema: `{"type":"object","properties":{"malformed_json":{"type":"string","description":"Raw broken, truncated, or markdown-wrapped JSON string to repair."},"repair_mode":{"type":"string","description":"Bracket-closing and literal-normalization strategy; defaults to 'heuristic_fast' when omitted.","enum":["heuristic_fast","strict_rfc8259","close_truncated_stream"]}},"required":["malformed_json"]}` ### enforce_json_schema_types — Strict JSON Schema Validator, Type Coercer & Field Pruner - Description: Validates a raw LLM output object against a target JSON Schema, automatically coercing mismatched scalar types (e.g. string '42' to integer 42), injecting schema defaults, and pruning undeclared hallucinated fields. Use when enforcing schema compliance and type safety on structured LLM outputs before passing them to typed APIs; for healing unparseable raw JSON text with broken quotes or trailing commas, use heal_malformed_json instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_output' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid. - Required Parameters: raw_output - Input Schema: `{"type":"object","properties":{"raw_output":{"type":"string","description":"JSON string or object produced by an LLM to validate and coerce."},"coercion_policy":{"type":"string","description":"Policy for handling extra undeclared properties; defaults to 'prune_undeclared_and_coerce' when omitted.","enum":["prune_undeclared_and_coerce","coerce_only_keep_extra","strict_reject_on_mismatch"]}},"required":["raw_output"]}` ### clean_tabular_dataset — Tabular Dataset & Text Deduplication, Whitespace & Normalization Engine - Description: Deduplicates repetitive lines or records, normalizes Unicode whitespace, strips HTML/control noise, and canonicalizes tabular text or JSON arrays. Use when cleaning noisy scraped lists, CSV rows, or duplicate log lines before indexing or analysis; for extracting typed JSON fields from free-form prose paragraphs, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'data' ('normalization_mode' defaults to 'exact_match'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: data - Input Schema: `{"type":"object","properties":{"data":{"type":"string","description":"Raw newline-delimited text, CSV rows, or JSON array string to deduplicate and normalize."},"normalization_mode":{"type":"string","description":"Deduplication key sensitivity; defaults to 'case_insensitive_trim' when omitted.","enum":["exact_match","case_insensitive_trim","alphanumeric_canonical"]}},"required":["data"]}` ### synthesize_safe_regex — Linear-Time O(n) ReDoS-Safe Regular Expression Synthesizer & Tester - Description: Synthesizes linear-time O(n) regular expressions free of catastrophic backtracking (ReDoS) and validates them against positive and negative test strings. Use when generating and verifying a regular expression pattern for input validation or lexical parsing; for repairing broken JSON syntax directly without writing custom regexes, use heal_malformed_json instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'description' ('flavor' defaults to 'ecmascript_js'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: description - Input Schema: `{"type":"object","properties":{"description":{"type":"string","description":"Natural-language specification of the text pattern to match (e.g. 'RFC 5322 email addresses excluding plus-aliases')."},"flavor":{"type":"string","description":"Target regular expression engine syntax; defaults to 'ecmascript_js' when omitted.","enum":["ecmascript_js","python_re","rust_regex_dfa","pcre2"]}},"required":["description"]}` ### compile_xml_agent_prompt — Production XML-Structured System Prompt & Guardrail Compiler - Description: Compiles a raw task description into a structured XML system prompt (, , , , , ) engineered to prevent instruction drift. Use when authoring or upgrading a system prompt for an autonomous agent or sub-agent workflow; for mapping a task objective to a concrete sequence of MCP tool calls, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('prompt_style' defaults to 'structured_xml_tags'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: task - Input Schema: `{"type":"object","properties":{"task":{"type":"string","description":"Raw task instructions, persona goal, and operational constraints to compile."},"prompt_style":{"type":"string","description":"Structural formatting template; defaults to 'structured_xml_tags' when omitted.","enum":["structured_xml_tags","markdown_sections","strict_json_responder"]}},"required":["task"]}` ### verify_context_compaction_fidelity — Pre/Post Context Compaction Information Retention Verifier - Description: Audits a compacted conversation summary against the original full context to detect dropped user constraints, lost file paths, altered numbers, or missing pending tasks. Use when verifying that an LLM context-compaction summary retained all task-critical facts before truncating history; for generating a new executive summary from a raw technical document, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'original_context' ('compacted_summary' defaults to 'standard'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: original_context, compacted_summary - Input Schema: `{"type":"object","properties":{"original_context":{"type":"string","description":"Full pre-compaction conversation history or task log."},"compacted_summary":{"type":"string","description":"Candidate compacted summary to audit for dropped constraints or entities."},"audit_focus":{"type":"string","description":"Entity class prioritized during retention scoring; defaults to 'constraints_paths_and_numbers' when omitted.","enum":["constraints_paths_and_numbers","code_identifiers_only","chronological_decisions"]}},"required":["original_context","compacted_summary"]}` ### route_mcp_workflow_plan — Autonomous Goal-to-MCP Tool Sequence Router & Cost Planner - Description: Maps a natural-language agent goal to an ordered sequence of Diogenes MCP tool calls with exact endpoint paths, JSON-RPC 2.0 payloads, and cumulative satoshi cost estimates. Use when an autonomous agent needs to plan which MCP tools to chain together to solve a multi-step objective within a satoshi budget; for compiling a static XML system prompt rather than an executable MCP tool call sequence, use compile_xml_agent_prompt instead. Read-only edge call (32 KB, 60 RPM): accepts 'objective' ('budget_preference' defaults to 'lowest_sats_deterministic'), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: objective - Input Schema: `{"type":"object","properties":{"objective":{"type":"string","description":"Natural-language description of the workflow goal to route across MCP tools."},"budget_preference":{"type":"string","description":"Cost vs depth routing trade-off; defaults to 'lowest_sats_deterministic' when omitted.","enum":["lowest_sats_deterministic","max_verification_depth","single_tool_fast"]}},"required":["objective"]}` ### arbitrate_agent_deliverable_escrow — Multi-Agent Task Deliverable & Contract Fulfillment Escrow Arbiter - Description: Evaluates a worker agent's submitted task deliverable against agreed contract acceptance criteria to issue a deterministic escrow settlement verdict ('RELEASE_FUNDS_TO_WORKER_AGENT', 'REQUEST_REVISION', or 'REFUND_CLIENT'). Use when settling multi-agent bounties or verifying subcontractor deliverables before releasing MPP/L402 escrow funds; for checking syntactic JSON Schema property types without evaluating semantic contract terms, use enforce_json_schema_types instead. Read-only call (32 KB, 60 RPM): accepts 'deliverable' (with enum defaults), uses '?demo=true' or MPP (30 sats); HTTP 400 if invalid. - Required Parameters: deliverable - Input Schema: `{"type":"object","properties":{"deliverable":{"type":"string","description":"JSON string or text deliverable submitted by the worker agent."},"terms":{"type":"string","description":"Contract acceptance criteria that the deliverable must satisfy; defaults to 'Complete verified JSON deliverable' when omitted."},"arbitration_standard":{"type":"string","description":"Strictness of contract verification; defaults to 'strict_all_criteria' when omitted.","enum":["strict_all_criteria","substantial_completion","schema_only"]}},"required":["deliverable"]}` ### prune_context_skeleton — AST-Aware Context Window & Source Code Skeleton Pruner - Description: Compresses large source files, logs, or transcripts by 50–80% to fit an LLM context budget while preserving 100% of function/class/type signatures, imports, error frames, and query-matched lines. Use when shrinking oversized source files or logs before feeding them into an LLM prompt; for counting BPE tokens across prompt segments and calculating multi-model inference costs without altering text, use plan_context_token_budget instead. Read-only edge call (32 KB, 60 RPM): accepts 'content' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid. - Required Parameters: content - Input Schema: `{"type":"object","properties":{"content":{"type":"string","description":"Raw source code, document, or multi-turn transcript to compress."},"target_ratio":{"type":"number","description":"Target token retention ratio between 0.15 and 0.85; defaults to 0.45 when omitted."},"focus_query":{"type":"string","description":"Optional symbol or keyword query whose matching lines receive maximum retention priority."},"pruning_mode":{"type":"string","description":"Salience weighting preset; defaults to 'ast_signatures_first' when omitted.","enum":["ast_signatures_first","errors_and_stackframes","prose_headings_first"]}},"required":["content"]}` ### plan_context_token_budget — BPE Token Budget, Attention Trough & Multi-Model Cost Planner - Description: Counts subword BPE tokens across prompt segments, detects high-priority instructions trapped in the 35%–72% Lost-in-the-Middle attention trough, and calculates USD/satoshi costs across frontier LLMs. Use when auditing prompt token budgets, reordering prompt sections for primacy/recency attention, or comparing model API costs; for actively compressing and stripping low-salience lines from a single large file, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'segments_json' (with enum defaults), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid. - Required Parameters: segments_json - Input Schema: `{"type":"object","properties":{"segments_json":{"type":"string","description":"JSON string or array of prompt segments '[{\"name\":\"sys\",\"text\":\"...\",\"priority\":10}]' to analyze."},"max_context_tokens":{"type":"number","description":"Target model context window limit in tokens; defaults to 128000 when omitted."},"target_model_family":{"type":"string","description":"Primary model family for token-Window calibration; defaults to 'gemini_3_1' when omitted.","enum":["gemini_3_1","claude_4_5","gpt_5","deepseek_r1"]}},"required":["segments_json"]}` ### rerank_hybrid_rag_chunks — Okapi BM25 + Reciprocal Rank Fusion (RRF) + MMR Chunk Reranker - Description: Reranks and deduplicates candidate RAG or retrieval passages against a search prompt using Okapi BM25 (k1=1.5, b=0.75), Reciprocal Rank Fusion (RRF), and Maximal Marginal Relevance (MMR) Jaccard diversity filtering. Use when selecting the top-K highest-signal, non-redundant passages from vector search or grep results; for compressing a single contiguous source file while keeping its original line order, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'search_prompt' ('documents_json' defaults to 'standard'), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid. - Required Parameters: search_prompt, documents_json - Input Schema: `{"type":"object","properties":{"search_prompt":{"type":"string","description":"Technical search prompt or question used to score candidate chunks."},"documents_json":{"type":"string","description":"JSON string or array of candidate chunks '[{\"id\":\"c1\",\"text\":\"...\"}]' to rerank."},"top_k":{"type":"number","description":"Maximum number of deduplicated chunks to return; defaults to 5 when omitted."},"ranking_mode":{"type":"string","description":"Fusion weighting between lexical BM25 and diversity penalty; defaults to 'bm25_rrf_mmr' when omitted.","enum":["bm25_rrf_mmr","pure_bm25_lexical","high_diversity_mmr"]}},"required":["search_prompt","documents_json"]}` ### apply_fuzzy_code_patch — Self-Healing Fuzzy Unified Diff & Search/Replace Code Patcher - Description: Applies unified diffs (@@ ... @@) or SEARCH/REPLACE blocks to source code using sliding-window token similarity to resolve drifted line numbers, align indentation, and verify bracket balance. Use when healing and applying a code edit or diff that failed exact line matching due to line-number drift or whitespace differences; for inspecting function signatures, call trees, and cyclomatic complexity without modifying code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'original_code' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: original_code, patch - Input Schema: `{"type":"object","properties":{"original_code":{"type":"string","description":"Complete original source file content before patching."},"patch":{"type":"string","description":"Unified diff hunk or <<<<<<< SEARCH ... ======= ... >>>>>>> REPLACE block to apply."},"fuzz_strategy":{"type":"string","description":"Line-matching tolerance and indentation behavior; defaults to 'whitespace_normalized_auto_indent' when omitted.","enum":["whitespace_normalized_auto_indent","exact_line_match","aggressive_token_fuzzy"]}},"required":["original_code","patch"]}` ### analyze_ast_symbol_graph — Polyglot AST Symbol Extractor, Call Graph & Complexity Analyzer - Description: Static lexer and AST parser only (zero execution or evaluation): extracts imports, exports, classes, interfaces, and functions with line numbers, intra-file call edges, McCabe cyclomatic complexity, and Halstead volume across TypeScript, Python, Rust, Go, and Move. Use when mapping internal functions, call graphs, and complexity hotspots of a source file before refactoring; for analyzing cross-file import DAGs and circular dependencies, use audit_module_dependency_cycles instead. Read-only call (32 KB, 60 RPM): accepts 'source_text' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: code - Input Schema: `{"type":"object","properties":{"code":{"type":"string","description":"Source code file content to parse for symbols and complexity metrics."},"source_text":{"type":"string","description":"Alias for code: source code file content to parse."},"language":{"type":"string","description":"Programming language grammar used for symbol extraction; defaults to 'typescript' when omitted.","enum":["typescript","python","rust","go","sui_move"]}},"required":["code"]}` ### audit_module_dependency_cycles — Tarjan SCC Circular Import Detector & Topological Blast-Radius Solver - Description: Runs Tarjan's Strongly Connected Components (SCC) algorithm on a module import map to detect circular dependencies, compute parallel topological build waves, and trace downstream change blast radius. Use when auditing multi-file import graphs for circular cycles or determining which downstream files must be re-tested after an edit; for extracting function-level symbols and cyclomatic complexity inside a single source file, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'modules_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: modules_json - Input Schema: `{"type":"object","properties":{"modules_json":{"type":"string","description":"JSON string or object mapping each module name to its array of imported module names (e.g. '{\"a\":[\"b\"],\"b\":[]}')."},"analysis_scope":{"type":"string","description":"Graph analysis output mode; defaults to 'cycles_waves_and_blast_radius' when omitted.","enum":["cycles_waves_and_blast_radius","cycles_only","topological_waves_only"]}},"required":["modules_json"]}` ### isolate_stacktrace_root_cause — Stack-Trace Root-Cause Frame Isolator & Drain Log Deduplicator - Description: Parses noisy CI/terminal logs and multi-language stack traces (Node/TS, Python, Rust, Go), strips node_modules/stdlib frames to isolate the innermost failing user-code frame, and clusters repetitive logs into Drain templates. Use when triage-debugging test failures, crash dumps, or repetitive server error logs; for compressing general source code files or prose transcripts, use prune_context_skeleton instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_log' ('runtime_hint' defaults to 'auto_detect'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: raw_log - Input Schema: `{"type":"object","properties":{"raw_log":{"type":"string","description":"Raw terminal output, CI failure log, or exception traceback to analyze."},"runtime_hint":{"type":"string","description":"Runtime stack format hint; defaults to 'auto_detect' when omitted.","enum":["auto_detect","nodejs_v8","python_traceback","rust_panic","go_goroutine"]}},"required":["raw_log"]}` ### compile_polyglot_type_schemas — Polyglot JSON -> TypeScript, Zod, Pydantic v2 & JSON Schema Compiler - Description: Inspects a sample JSON payload (inferring UUID, ISO-8601 datetime, email, integer vs float, and array item types) and compiles strict TypeScript interfaces, Zod schemas, Python Pydantic v2 models, and JSON Schema Draft 2020-12. Use when generating static type definitions and runtime validators in TypeScript and Python from a sample JSON response; for extracting existing function/class symbols and complexity metrics from source code, use analyze_ast_symbol_graph instead. Read-only call (32 KB, 60 RPM): accepts 'sample_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: sample_json - Input Schema: `{"type":"object","properties":{"sample_json":{"type":"string","description":"JSON string or object representing the sample payload to infer types from."},"root_name":{"type":"string","description":"Identifier used for the generated root interface/class; defaults to 'GeneratedPayload' when omitted."},"strictness":{"type":"string","description":"Schema additionalProperties and format constraint mode; defaults to 'strict_formats' when omitted.","enum":["strict_formats","passthrough_open","partial_optional"]}},"required":["sample_json"]}` ### evaluate_deterministic_math — Shunting-Yard Algebraic Math, Financial IRR/NPV & Descriptive Stats Solver - Description: Strict Shunting-Yard AST arithmetic parser with zero eval() or dynamic code execution: evaluates algebraic formulas and computes exact financial NPV, Newton-Raphson IRR, Kelly criterion, and dataset stats. Use when computing exact arithmetic formulas, cashflow NPV/IRR, or descriptive statistics without LLM floating-point guesswork; for running two-sample A/B hypothesis tests, use evaluate_ab_statistical_significance instead. Read-only edge call (32 KB, 60 RPM): accepts 'math_formula' ('precision_digits' defaults to '2_decimals'), uses '?demo=true' or L402 (10 sats); HTTP 400 if invalid. - Required Parameters: expression - Input Schema: `{"type":"object","properties":{"expression":{"type":"string","description":"Algebraic or scientific formula to evaluate (e.g. '(125000 * (1 + 0.0725/12)^60) - 98450.50')."},"math_formula":{"type":"string","description":"Alias for expression: algebraic formula to evaluate."},"precision_digits":{"type":"string","description":"Decimal rounding precision for returned numbers; defaults to '8_decimals' when omitted.","enum":["2_decimals","4_decimals","8_decimals"]}},"required":["expression"]}` ### schedule_critical_path_tasks — Critical Path Method (CPM) DAG & Resource Constraint Scheduler - Description: Solves a task dependency DAG via the Critical Path Method (CPM) to compute ES/EF/LS/LF, Total Float/Slack, optimal makespan, and the Critical Path. Use when scheduling dependent engineering milestones or workflow steps to find the minimum project duration and zero-slack bottleneck path; for detecting circular code imports and file blast radius without task durations, use audit_module_dependency_cycles instead. Read-only edge call (32 KB, 60 RPM): accepts 'tasks_json' ('time_unit' defaults to 'minutes'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: tasks_json - Input Schema: `{"type":"object","properties":{"tasks_json":{"type":"string","description":"JSON string or array of tasks '[{\"id\":\"t1\",\"duration\":3,\"dependencies\":[]}]' to schedule."},"time_unit":{"type":"string","description":"Duration unit label attached to the schedule; defaults to 'hours' when omitted.","enum":["minutes","hours","days","sprints"]}},"required":["tasks_json"]}` ### evaluate_ab_statistical_significance — Welch's t-Test, Two-Proportion z-Test & Bayesian A/B Eval Judge - Description: Computes Welch's two-sample t-test or two-proportion z-test, returning two-tailed p-values, Cohen's d effect size, relative lift %, and Bayesian P(Treatment > Control). Use when determining whether a prompt change, model benchmark, or A/B experiment produced a statistically significant improvement; for evaluating single algebraic formulas or NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'control_json' ('treatment_json' defaults to 'standard'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: control_json, treatment_json - Input Schema: `{"type":"object","properties":{"control_json":{"type":"string","description":"JSON string or object for the baseline control arm (e.g. '{\"conversions\":142,\"total\":1000}' or '{\"samples\":[12,15,14]}')."},"treatment_json":{"type":"string","description":"JSON string or object for the candidate treatment arm (e.g. '{\"conversions\":186,\"total\":1000}')."},"significance_level":{"type":"string","description":"Type-I error alpha threshold for statistical significance; defaults to 'alpha_0_05' when omitted.","enum":["alpha_0_01","alpha_0_05","alpha_0_10"]}},"required":["control_json","treatment_json"]}` ### detect_openapi_breaking_changes — OpenAPI 3.1, JSON Schema & MCP Contract Breaking-Change Detector - Description: Compares baseline and candidate OpenAPI 3.1 specs, JSON Schemas, or MCP tool manifests to detect breaking changes (removed fields, new required inputs, narrowed enums, type mutations). Use when auditing API, JSON Schema, or MCP contract revisions for backward compatibility before deployment; for compiling new TypeScript, Zod, and Pydantic schemas from a single sample JSON payload, use compile_polyglot_type_schemas instead. Read-only edge call (32 KB, 60 RPM): accepts 'baseline_schema_json' (with enum defaults), uses '?demo=true' or L402 (25 sats); HTTP 400 if invalid. - Required Parameters: baseline_schema_json, candidate_schema_json - Input Schema: `{"type":"object","properties":{"baseline_schema_json":{"type":"string","description":"JSON string of the baseline OpenAPI 3.1 spec, JSON Schema, or MCP tools array."},"candidate_schema_json":{"type":"string","description":"JSON string of the proposed candidate schema or contract revision to compare."},"contract_format":{"type":"string","description":"Contract specification format; defaults to 'auto_detect' when omitted.","enum":["auto_detect","json_schema","openapi_3_1","mcp_tools_manifest"]}},"required":["baseline_schema_json","candidate_schema_json"]}` ### generate_boundary_test_vectors — JSON Schema & Function Signature Boundary-Value Test Vector Generator - Description: Synthesizes deterministic unit-test vectors from a JSON Schema or function signature covering valid equivalence partitions, numeric/length boundaries, and adversarial Unicode/null inputs. Use when generating exhaustive edge-case unit test payloads and fuzz vectors for an API endpoint or function; for healing and applying unified diffs or search/replace edits to source code, use apply_fuzzy_code_patch instead. Read-only edge call (32 KB, 60 RPM): accepts 'schema_or_signature_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: schema_or_signature_json - Input Schema: `{"type":"object","properties":{"schema_or_signature_json":{"type":"string","description":"JSON Schema object or function parameter specification to generate test vectors for."},"vector_suite_profile":{"type":"string","description":"Test generation coverage profile; defaults to 'equivalence_boundary_and_fuzz' when omitted.","enum":["equivalence_boundary_and_fuzz","boundary_values_only","adversarial_security_fuzz"]}},"required":["schema_or_signature_json"]}` ### simulate_monte_carlo_risk — Seeded Mulberry32 Monte Carlo Percentile, VaR & Tail-Risk Simulator - Description: Runs a reproducible seeded Mulberry32 Monte Carlo simulation over uncertain cost, latency, or duration variables to compute P10/P50/P90/P95 percentiles, Value-at-Risk (VaR), and CVaR. Use when modeling stochastic uncertainty, tail risk (VaR/CVaR), and probability of meeting a budget or SLA target; for evaluating deterministic single-point algebraic formulas or exact NPV/IRR cashflows, use evaluate_deterministic_math instead. Read-only edge call (32 KB, 60 RPM): accepts 'variables_json' (with enum defaults), uses '?demo=true' or L402 (20 sats); HTTP 400 if invalid. - Required Parameters: variables_json - Input Schema: `{"type":"object","properties":{"variables_json":{"type":"string","description":"JSON array of stochastic variables (e.g. name, min, mode, max) to simulate."},"distribution_model":{"type":"string","description":"Probability distribution family applied to each variable; defaults to 'triangular_pert' when omitted.","enum":["triangular_pert","normal_gaussian","uniform_range"]}},"required":["variables_json"]}` ### scan_solana_cpi_reentrancy — Solana Anchor & Rust Cross-Program Invocation (CPI) Vulnerability Scanner - Description: Scans Solana Anchor and native Rust program instructions for unverified Cross-Program Invocation (CPI) program IDs, missing signer checks, and PDA bump seed canonicalization bugs. Use when auditing Solana Rust/Anchor source code or instruction account structs for CPI privilege escalation; for checking live SPL token mint/freeze authorities and rug-pull risk by mint address, use evaluate_solana_token_risk instead. Read-only edge call (32 KB, 60 RPM): accepts 'rust_source_or_idl' ('framework' defaults to 'anchor'), uses '?demo=true' or L402 (30 sats); HTTP 400 if invalid. - Required Parameters: rust_source_or_idl - Input Schema: `{"type":"object","properties":{"rust_source_or_idl":{"type":"string","description":"Solana Rust/Anchor source code or IDL JSON string to scan for CPI vulnerabilities."},"framework":{"type":"string","description":"Solana program framework used; defaults to 'anchor' when omitted.","enum":["anchor","native_rust_solana","pinocchio"]}},"required":["rust_source_or_idl"]}` ### evaluate_solana_token_risk — Solana SPL Token Mint/Freeze Authority & Rug-Pull Risk Evaluator - Description: Evaluates Solana SPL and Token-2022 rug-pull risk by checking mint/freeze authorities, permanent delegates, transfer hooks, and returning reason codes with slot height. Use when making a pre-trade security decision on whether an SPL or Token-2022 mint is safe to trade; for DEX liquidity and metadata lookup via x402, use inspect_solana_token_liquidity instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token_address' ('risk_profile' defaults to 'strict_decentralized'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: token_address - Input Schema: `{"type":"object","properties":{"token_address":{"type":"string","description":"Base58-encoded Solana SPL token mint address (32–44 characters)."},"risk_profile":{"type":"string","description":"Tolerance policy for centralized freeze authorities; defaults to 'strict_decentralized' when omitted.","enum":["strict_decentralized","allow_regulated_stablecoins","memecoin_sniping"]}},"required":["token_address"]}` ### inspect_solana_token_liquidity — Solana SPL Token Metadata, Decimals & Authority Registry Lookup - Description: Retrieves canonical Solana SPL token metadata including name, ticker symbol, decimal precision, and current mint/freeze authority addresses. Use when resolving SPL token decimals, ticker symbols, and registry metadata for portfolio or swap formatting; for computing a composite security risk score and binary should_transact verdict, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'mint' ('network' defaults to 'mainnet-beta'), supports '?demo=true' or x402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: mint - Input Schema: `{"type":"object","properties":{"mint":{"type":"string","description":"Base58-encoded Solana SPL token mint address (e.g. 'EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v')."},"network":{"type":"string","description":"Solana cluster to query; defaults to 'mainnet-beta' when omitted.","enum":["mainnet-beta","devnet"]}},"required":["mint"]}` ### track_solana_whale_flows — Solana Whale Wallet Net-Flow & Insider Cluster Tracker - Description: Tracks 24-hour net accumulation or distribution flows across top Solana whale wallets and flags coordinated insider wallet clusters for a given SPL token. Use when analyzing on-chain smart-money order flow and holder clustering on Solana; for checking static SPL contract mint/freeze authority permissions, use evaluate_solana_token_risk instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'token' ('window' defaults to '1h'), supports '?demo=true' or x402 (50 sats), and returns HTTP 400 if invalid. - Required Parameters: token - Input Schema: `{"type":"object","properties":{"token":{"type":"string","description":"Base58 Solana SPL token mint address or ticker symbol to track whale flows for."},"window":{"type":"string","description":"Aggregation lookback window for net whale flow; defaults to '24h' when omitted.","enum":["1h","6h","24h","7d"]}},"required":["token"]}` ### estimate_solana_priority_fees — Solana Compute-Unit Priority Fee & Jito MEV Tip Estimator - Description: Calculates optimal Solana compute-unit (CU) microlamport priority fees and Jito bundle tip lamports to achieve target block-inclusion probability. Use when setting SetComputeUnitPrice and Jito tips before broadcasting a Solana transaction; for querying Bitcoin L1 sat/vB mempool fee rates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'priority_level' ('tx_type' defaults to 'simple_transfer'), supports '?demo=true' or x402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: priority_level - Input Schema: `{"type":"object","properties":{"priority_level":{"type":"string","description":"Target inclusion urgency tier on Solana mainnet-beta.","enum":["low","medium","high","ultra"]},"tx_type":{"type":"string","description":"Transaction category used to estimate compute unit limit; defaults to 'dex_swap' when omitted.","enum":["simple_transfer","dex_swap","nft_mint","arbitrary_cpi"]}},"required":["priority_level"]}` ### decode_eip712_permit_signature — EIP-712 Typed Data & Uniswap Permit2 Phishing Signature Decoder - Description: Decodes EIP-712 and Uniswap Permit2 off-chain typed-data payloads to verify spender identity, detect unlimited (uint256.max) token approvals, and flag expired deadlines. Use when inspecting an off-chain eth_signTypedData_v4 or Permit2 payload before signing; for decoding raw on-chain hex transaction calldata (0x...) for eth_sendTransaction, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'typed_data_json' ('chain_id' defaults to '1'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: typed_data_json - Input Schema: `{"type":"object","properties":{"typed_data_json":{"type":"string","description":"JSON string or object containing the EIP-712 / Permit2 message (spender, amount, deadline)."},"chain_id":{"type":"string","description":"EVM chain ID used to verify canonical router spender addresses; defaults to '8453' (Base) when omitted.","enum":["1","8453","42161","10"]}},"required":["typed_data_json"]}` ### simulate_evm_transaction_calldata — Pre-Sign EVM Hex Calldata Selector Decoder & Drain Simulator - Description: Decodes raw EVM hexadecimal transaction calldata (0x...) by 4-byte function selector to expose hidden ERC-20 approve/transferFrom calls, setApprovalForAll drains, and multicall bundles. Use when auditing raw hex transaction data (to, value, data) before broadcasting an on-chain EVM transaction; for inspecting off-chain EIP-712 JSON typed-data signatures, use decode_eip712_permit_signature instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'calldata_hex' ('network' defaults to 'base_mainnet'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: calldata_hex - Input Schema: `{"type":"object","properties":{"calldata_hex":{"type":"string","description":"Hexadecimal EVM transaction data string starting with '0x' (e.g. '0x095ea7b3000000000000000000000000...')."},"network":{"type":"string","description":"Target EVM network for simulation context; defaults to 'base_mainnet' when omitted.","enum":["base_mainnet","ethereum_mainnet","arbitrum_one","optimism"]}},"required":["calldata_hex"]}` ### evaluate_dex_mev_risk — Pre-Swap DEX MEV Sandwich & Frontrunning Risk Evaluator - Description: Evaluates decentralized exchange (DEX) swap parameters against pool depth and mempool visibility to quantify MEV sandwich risk and compute optimal slippage tolerance in basis points. Use when configuring slippage tolerance and private-RPC routing before executing an on-chain DEX token swap; for comparing cross-chain bridge settlement routes across different L1 blockchains, use compare_crosschain_bridge_routes instead. Read-only edge call (32 KB, 60 RPM): accepts 'pair' ('execution_venue' defaults to 'uniswap_v3_public'), uses '?demo=true' or L402 (25 sats); HTTP 400 if invalid. - Required Parameters: pair - Input Schema: `{"type":"object","properties":{"pair":{"type":"string","description":"Trading pair symbol or pool identifier (e.g. 'ETH/USDC' or 'SOL/USDC')."},"execution_venue":{"type":"string","description":"Target DEX protocol or RPC relay; defaults to 'uniswap_v3_public' when omitted.","enum":["uniswap_v3_public","flashbots_protect","aerodrome_base","jupiter_jito"]}},"required":["pair"]}` ### detect_address_poisoning_scam — Counterparty Address Poisoning & Vanity Prefix/Suffix Spoof Detector - Description: Compares a target recipient wallet address against recent transaction history to detect vanity prefix/suffix lookalike spoofing and zero-value dusting attacks. Use when verifying a recipient EVM or Solana wallet address before sending funds; for decoding hex smart contract calldata payloads, use simulate_evm_transaction_calldata instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_address' ('address_standard' defaults to 'auto_detect'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: target_address - Input Schema: `{"type":"object","properties":{"target_address":{"type":"string","description":"Candidate recipient EVM (0x...) or Solana Base58 wallet address to verify."},"address_standard":{"type":"string","description":"Address encoding format; defaults to 'auto_detect' when omitted.","enum":["auto_detect","evm_hex","solana_base58"]}},"required":["target_address"]}` ### verify_http402_payment_challenge — Pre-Payment HTTP 402 (L402 / x402 / MPP) Invoice & Macaroon Fraud Verifier - Description: Decodes inbound HTTP 402 Payment Required challenges (L402 BOLT11 + Macaroon, x402 Solana USDC, MPP Base intents) to verify cryptographic payment-hash binding and block overcharge fraud. Use when auditing a 402 challenge header before an autonomous agent pays a Lightning invoice or USDC transfer; for checking on-chain Bitcoin L1 mempool feerates, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'www_authenticate' ('protocol_hint' defaults to 'L402'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: www_authenticate - Input Schema: `{"type":"object","properties":{"www_authenticate":{"type":"string","description":"Raw WWW-Authenticate or Payment-Required HTTP header string from a 402 response."},"protocol_hint":{"type":"string","description":"Expected HTTP 402 payment protocol; defaults to 'L402' when omitted.","enum":["L402","x402","MPP"]}},"required":["www_authenticate"]}` ### estimate_bitcoin_mempool_fees — Bitcoin Mainnet Mempool Feerate Estimator (sat/vB) - Description: Fetches real-time Bitcoin mainnet mempool feerate recommendations in satoshis per virtual byte (sat/vB) across fastest, half-hour, hour, and economy confirmation tiers. Use when checking current Bitcoin L1 network congestion before broadcasting an on-chain BTC transaction; for calculating exact SegWit/Taproot UTXO batch consolidation vByte weights and dust thresholds, use plan_bitcoin_utxo_consolidation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'confirmation_target', supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: none - Input Schema: `{"type":"object","properties":{"confirmation_target":{"type":"string","description":"Target confirmation speed tier; defaults to 'half_hour' when omitted.","enum":["fastest_block","half_hour","one_hour","economy"]}},"required":[]}` ### plan_bitcoin_utxo_consolidation — Bitcoin SegWit/Taproot UTXO Dust Consolidation & Fee-Window Planner - Description: Analyzes a set of Bitcoin UTXO balances in satoshis to compute exact vByte transaction weight, identify uneconomical dust inputs, and recommend whether to consolidate now or hold. Use when optimizing on-chain Bitcoin treasury UTXO sets to minimize long-term miner fee drag; for fetching current live Bitcoin mempool sat/vB feerates alone, use estimate_bitcoin_mempool_fees instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'utxos_sats_json' ('script_type' defaults to 'p2wpkh_segwit'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: utxos_sats_json - Input Schema: `{"type":"object","properties":{"utxos_sats_json":{"type":"string","description":"JSON array or comma-separated list of UTXO values in satoshis (e.g. '[1200, 45000, 85000]')."},"script_type":{"type":"string","description":"Bitcoin input script type determining vByte weight per input; defaults to 'p2wpkh_segwit' when omitted.","enum":["p2wpkh_segwit","p2tr_taproot","p2sh_nested"]}},"required":["utxos_sats_json"]}` ### calculate_spot_swap_rate — Cross-Asset Spot Exchange Rate & Satoshi Conversion Calculator - Description: Calculates instantaneous spot exchange rates and equivalent USD, BTC, and satoshi values across BTC, ETH, SOL, SUI, and USDC. Use when converting a token amount into USD or satoshis for invoice pricing or accounting; for quoting executable non-KYC cross-chain bridge routes with bridge fees and settlement times, use compare_crosschain_bridge_routes instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'currency' ('amount' defaults to 'standard'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: currency - Input Schema: `{"type":"object","properties":{"currency":{"type":"string","description":"Source asset ticker symbol to convert from.","enum":["USDC","BTC","ETH","SOL","SUI"]},"amount":{"type":"number","description":"Quantity of the source asset to convert; defaults to 100 when omitted."}},"required":["currency"]}` ### compare_crosschain_bridge_routes — Non-KYC Cross-Chain Bridge Route & Settlement Fee Comparator - Description: Compares non-custodial, non-KYC cross-chain swap routes (THORChain native L1 swaps, Maya Protocol, Blockstream Liquid) by basis-point fee, net output sats, and settlement time. Use when routing cross-chain treasury settlements (e.g. Solana USDC or Base ETH into native Bitcoin); for calculating mid-market spot exchange rates without bridge routing fees, use calculate_spot_swap_rate instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'from_asset' ('to_asset' defaults to 'BTC_NATIVE'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: from_asset - Input Schema: `{"type":"object","properties":{"from_asset":{"type":"string","description":"Origin chain asset identifier to bridge from.","enum":["USDC_SOL","USDC_BASE","ETH_BASE","SOL_NATIVE","BTC_NATIVE"]},"to_asset":{"type":"string","description":"Destination chain asset identifier; defaults to 'BTC_NATIVE' when omitted.","enum":["BTC_NATIVE","USDC_SOL","USDC_BASE","ETH_BASE"]},"amount":{"type":"number","description":"Input asset amount to quote; defaults to 100.0 when omitted."}},"required":["from_asset"]}` ### generate_gemini_completion — Account-Less Google Gemini 4 Argon & 3.1 Pro Universal Text Generator - Description: Generates text completions and structured reasoning across all 45 Google Gemini foundation models (Gemini 4 Argon, 3.1 Pro, 3.8 Flash) with zero Google account or API key required. Use when running single-turn reasoning, coding, or analytical prompts on a specific Gemini model; for delegating multi-step complex tasks that require remote tool execution, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('model' defaults to 'gemini-4-argon'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Primary user instruction or reasoning prompt to send to the selected Gemini model."},"model":{"type":"string","description":"Target Gemini foundation model identifier; defaults to 'gemini-4-argon' when omitted.","enum":["gemini-4-argon","gemini-3.1-pro","gemini-3.8-flash","gemini-2.5-pro"]}},"required":["prompt"]}` ### execute_antigravity_agent — Google Antigravity Multi-Step Autonomous Coding & Workflow Agent - Description: Dispatches a complex engineering or operational task to Google's Antigravity autonomous agent for multi-step planning, tool orchestration, and verified execution. Use when solving multi-stage software engineering or workflow tasks that require autonomous planning; for compiling exhaustive multi-source literature and market research dossiers, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('execution_mode' defaults to 'autonomous_verified'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid. - Required Parameters: input - Input Schema: `{"type":"object","properties":{"input":{"type":"string","description":"High-level task objective and constraints for the Antigravity autonomous agent."},"execution_mode":{"type":"string","description":"Autonomy policy for subtask execution; defaults to 'autonomous_verified' when omitted.","enum":["autonomous_verified","plan_only","strict_sandbox"]}},"required":["input"]}` ### conduct_deep_research_investigation — Gemini Deep Research Pro Multi-Hop Investigative Analyst - Description: Runs an iterative, multi-hop investigative research session via Gemini Deep Research Pro, cross-examining primary sources to produce a cited technical report. Use when investigating complex scientific, architectural, or market questions requiring deep multi-hop synthesis; for running a fast single-turn Google Search grounded fact lookup, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('depth_tier' defaults to 'quick_synthesis'), supports '?demo=true' or L402 (300 sats), and returns HTTP 400 if invalid. - Required Parameters: input - Input Schema: `{"type":"object","properties":{"input":{"type":"string","description":"Investigative research question, scope, and specific aspects to analyze."},"depth_tier":{"type":"string","description":"Research breadth and citation density; defaults to 'exhaustive_report' when omitted.","enum":["quick_synthesis","standard_brief","exhaustive_report"]}},"required":["input"]}` ### operate_computer_use_agent — Gemini Computer Use GUI & Browser Action Planner - Description: Plans and executes OS-level desktop, browser DOM, and GUI coordinate actions (click, type, scroll, wait) using the Gemini Computer Use agent. Use when automating interactive web UIs or desktop workflows that lack a direct REST API; for running code-first API and terminal automation tasks, use execute_antigravity_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('viewport_preset' defaults to 'desktop_1080p'), supports '?demo=true' or L402 (200 sats), and returns HTTP 400 if invalid. - Required Parameters: input - Input Schema: `{"type":"object","properties":{"input":{"type":"string","description":"UI automation goal and target webpage or application context."},"viewport_preset":{"type":"string","description":"Target screen resolution for coordinate grounding; defaults to 'desktop_1080p' when omitted.","enum":["desktop_1080p","laptop_720p","mobile_viewport"]}},"required":["input"]}` ### search_gemini_grounded_web — Google Search Grounded Real-Time Fact & Citation Engine - Description: Answers factual queries with live Google Search grounding, returning verified up-to-date answers accompanied by source URLs and grounding metadata. Use when verifying live web facts, documentation updates, or current events in a single low-latency call; for querying geographic places, coordinates, directions, and local business data via Google Maps grounding, use search_gemini_grounded_maps instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('recency_bias' defaults to 'past_24h'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Factual question or search query to ground against live Google Search results."},"recency_bias":{"type":"string","description":"Temporal preference for search snippets; defaults to 'any_time' when omitted.","enum":["past_24h","past_week","past_year","any_time"]}},"required":["prompt"]}` ### search_gemini_grounded_maps — Google Maps Grounded Geospatial & Place Intelligence Engine - Description: Executes geospatial and point-of-interest queries grounded in live Google Maps data, returning verified addresses, coordinates, operating hours, and spatial context. Use when resolving physical locations, venues, transit distances, or regional infrastructure data; for searching general web articles, documentation, and news, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('distance_units' defaults to 'metric_km'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Geospatial query, place name, or regional routing question."},"distance_units":{"type":"string","description":"Preferred unit system for distances; defaults to 'metric_km' when omitted.","enum":["metric_km","imperial_miles"]}},"required":["prompt"]}` ### compile_mpp_research_dossier — Base MPP Session-Metered Multi-Source Research Dossier Compiler - Description: Compiles a structured JSON research dossier ('key_findings', 'synthesis_quality_score', 'sources_cited') settled via Base EVM Machine Payments Protocol (MPP). Use when generating a strict-JSON cited intelligence brief paid via Base USDC MPP session headers; for running long-form narrative research reports via L402 Lightning, use conduct_deep_research_investigation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('output_density' defaults to 'concise_5_points'), supports '?demo=true' or MPP (300 sats), and returns HTTP 400 if invalid. - Required Parameters: query - Input Schema: `{"type":"object","properties":{"query":{"type":"string","description":"Research topic or technical question to investigate and structure into JSON."},"research_topic":{"type":"string","description":"Alias for query: research topic or technical question to investigate."},"output_density":{"type":"string","description":"Granularity of the key_findings array; defaults to 'executive_10_points' when omitted.","enum":["concise_5_points","executive_10_points","comprehensive_20_points"]}},"required":["query"]}` ### generate_gemini_embeddings — Gemini Embedding 2 High-Dimensional (3,072-D) Vector Generator - Description: Generates normalized 3,072-dimensional or 768-dimensional semantic vector embeddings via Google Gemini Embedding 2 for RAG indexing and cosine-similarity search. Use when embedding text passages or queries via L402 Lightning with configurable Matryoshka dimensions; for running live Google Search grounded factual queries, use search_gemini_grounded_web instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('model' defaults to 'gemini-embedding-2'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Input text passage, code snippet, or search query to embed into a float vector."},"model":{"type":"string","description":"Gemini embedding model version; defaults to 'gemini-embedding-2' when omitted.","enum":["gemini-embedding-2","gemini-embedding-1"]}},"required":["text"]}` ### analyze_omni_multimodal_input — Gemini Omni Unified Text, Audio & Video Multimodal Analyzer - Description: Analyzes combined multimodal prompts spanning text, image descriptors, audio transcripts, and video temporal events using Gemini Omni Flash. Use when correlating information across multiple media modalities in a single reasoning pass; for running pure text-only reasoning or coding prompts, use generate_gemini_completion instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('modality_focus' defaults to 'cross_modal_synthesis'), supports '?demo=true' or L402 (100 sats), and returns HTTP 400 if invalid. - Required Parameters: input - Input Schema: `{"type":"object","properties":{"input":{"type":"string","description":"Multimodal prompt or media scene description to analyze."},"modality_focus":{"type":"string","description":"Primary analytical lens applied to the multimodal input; defaults to 'cross_modal_synthesis' when omitted.","enum":["cross_modal_synthesis","visual_ocr_extraction","temporal_event_timeline"]}},"required":["input"]}` ### plan_robotics_spatial_trajectory — Gemini Robotics ER 2 Embodied Spatial & Kinematics Trajectory Planner - Description: Computes 3D spatial affordances, obstacle-avoidance waypoints, and manipulator grasp sequences using Gemini Robotics ER 2 embodied reasoning. Use when planning physical robot arm kinematics, mobile navigation waypoints, or spatial scene task orders; for interacting with 2D desktop or browser GUI screens, use operate_computer_use_agent instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('coordinate_frame' defaults to 'cartesian_xyz_meters'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Spatial environment description, obstacle coordinates, and physical manipulation goal."},"coordinate_frame":{"type":"string","description":"Reference coordinate convention; defaults to 'cartesian_xyz_meters' when omitted.","enum":["cartesian_xyz_meters","joint_angles_radians","normalized_voxel_grid"]}},"required":["prompt"]}` ### generate_nano_banana_image — Nano Banana Pro (Gemini Image) Visual Asset & Diagram Generator - Description: Generates photorealistic illustrations, UI mockups, and technical diagrams from text prompts using the Nano Banana Pro (Gemini 2.5 Flash Image) model family. Use when creating static visual assets, icons, or architecture diagrams from text descriptions; for synthesizing animated multi-second video clips with motion, use generate_veo_cinematic_video instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('aspect_ratio' defaults to '1:1'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Detailed visual scene, composition, lighting, and typography description to render."},"aspect_ratio":{"type":"string","description":"Output image aspect ratio; defaults to '16:9' when omitted.","enum":["1:1","16:9","9:16","4:3"]}},"required":["prompt"]}` ### generate_veo_cinematic_video — Google Veo 3 High-Definition Cinematic Video Generator - Description: Synthesizes high-definition cinematic video sequences with temporally coherent camera motion and physics using Google Veo 3. Use when generating moving video clips, product B-roll, or animated scene renders from text prompts; for rendering static single-frame images or diagrams at lower cost, use generate_nano_banana_image instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('motion_style' defaults to 'static_tripod'), supports '?demo=true' or L402 (650 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Cinematic scene description including subject motion, camera trajectory, and lighting."},"motion_style":{"type":"string","description":"Camera movement preset; defaults to 'smooth_tracking_shot' when omitted.","enum":["static_tripod","smooth_tracking_shot","drone_fpv_flyover","macro_slow_motion"]}},"required":["prompt"]}` ### compose_lyria_music_track — Google Lyria 3 Instrumental Music & Audio Stem Composer - Description: Composes studio-grade instrumental music tracks, ambient loops, and multi-instrument arrangements from genre, tempo, and mood prompts using Google Lyria 3. Use when generating musical scores, soundtrack stems, or rhythmic audio loops; for converting written text into spoken human voice narration (TTS), use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('genre_preset' defaults to 'cinematic_synth'), supports '?demo=true' or L402 (150 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Musical style, instrumentation, BPM tempo, and harmonic mood description."},"genre_preset":{"type":"string","description":"Primary acoustic or electronic genre; defaults to 'cinematic_synth' when omitted.","enum":["cinematic_synth","lo_fi_hiphop","orchestral_ambient","industrial_techno"]}},"required":["prompt"]}` ### synthesize_gemini_speech_audio — Gemini Neural Text-to-Speech (TTS) Expressive Voice Synthesizer - Description: Converts written text into natural, prosody-controlled spoken voice audio using Gemini 3.8 Flash Neural Text-to-Speech. Use when rendering voiceover narration or spoken agent replies from a deterministic text script; for conducting bidirectional conversational audio dialog comprehension, use process_live_audio_dialogue instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('voice_persona' defaults to 'neutral_broadcast'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Exact written script or paragraph to synthesize into spoken voice audio."},"voice_persona":{"type":"string","description":"Expressive vocal timbre preset; defaults to 'neutral_broadcast' when omitted.","enum":["neutral_broadcast","warm_conversational","technical_lecturer","urgent_alert"]}},"required":["text"]}` ### process_live_audio_dialogue — Gemini 3.8 Live Native Audio-to-Audio Conversational Processor - Description: Processes real-time conversational dialog turns with native acoustic emotion, interruption handling, and paralinguistic cue comprehension via Gemini 3.8 Live. Use when handling interactive voice-agent dialog turns that require tone and turn-taking awareness; for performing one-way text-to-speech readout of a static text string, use synthesize_gemini_speech_audio instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'input' ('response_tone' defaults to 'direct_peer'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: input - Input Schema: `{"type":"object","properties":{"input":{"type":"string","description":"Conversational audio transcript or dialog turn payload to process."},"response_tone":{"type":"string","description":"Target paralinguistic delivery style; defaults to 'direct_peer' when omitted.","enum":["direct_peer","concise_tactical","empathetic_support"]}},"required":["input"]}` ### extract_structured_json_entities — Unstructured Text to Typed JSON Entity & Record Extractor - Description: Extracts structured JSON records, named entities, dates, and financial figures from unstructured prose, emails, or HTML/Markdown dumps. Use when converting unstructured natural-language text into a structured JSON array of entities; for validating and coercing an existing JSON payload against a formal JSON Schema, use enforce_json_schema_types instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('extraction_target' defaults to 'general_entities_and_metrics'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Unstructured document, email body, or webpage text to extract structured entities from."},"extraction_target":{"type":"string","description":"Primary entity domain to extract; defaults to 'general_entities_and_metrics' when omitted.","enum":["general_entities_and_metrics","contacts_and_organizations","financial_line_items","timeline_events"]}},"required":["text"]}` ### synthesize_python_automation_code — Self-Contained Python Script, CLI & Parser Code Synthesizer - Description: Synthesizes PEP 8 compliant, self-contained Python 3 scripts, data parsers, and CLI utilities complete with type hints, docstrings, and inline assertion tests. Use when generating a standalone Python automation script or parser from a functional specification; for summarizing existing documentation or codebases into executive bullet points, use summarize_technical_document instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'prompt' ('dependency_policy' defaults to 'stdlib_only'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: prompt - Input Schema: `{"type":"object","properties":{"prompt":{"type":"string","description":"Functional specification, input/output formats, and edge cases for the Python script."},"dependency_policy":{"type":"string","description":"Allowed library dependencies in generated code; defaults to 'stdlib_only' when omitted.","enum":["stdlib_only","allow_requests_and_pydantic","async_httpx_tokio"]}},"required":["prompt"]}` ### summarize_technical_document — High-Density Technical Document & RFC Executive Summarizer - Description: Condenses long technical specifications, RFCs, research papers, or meeting transcripts into high-density executive bullet points preserving exact figures and decisions. Use when producing a human-readable executive summary of a single provided document; for researching a topic across the live web with Google Search citations, use synthesize_web_intelligence_brief instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('summary_format' defaults to 'executive_bullets'), supports '?demo=true' or L402 (50 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Full document text, RFC, or transcript to summarize."},"summary_format":{"type":"string","description":"Output presentation structure; defaults to 'executive_bullets' when omitted.","enum":["executive_bullets","decision_log_table","one_paragraph_abstract"]}},"required":["text"]}` ### synthesize_web_intelligence_brief — Real-Time Google Search Grounded JSON Market Intelligence Brief - Description: Synthesizes a real-time market or technical intelligence brief grounded in live Google Search, returning strict JSON ('executive_summary', 'key_developments', 'sentiment', 'sources'). Use when fetching a structured JSON market/news brief with live web citations and sentiment classification; for summarizing caller-supplied text offline without live web search, use summarize_technical_document instead. Read-only edge call (32 KB, 60 RPM): accepts 'topic' ('focus' defaults to 'technical_and_market_catalysts'), supports '?demo=true' or L402 (75 sats), and returns HTTP 400 if invalid. - Required Parameters: topic - Input Schema: `{"type":"object","properties":{"topic":{"type":"string","description":"Company, protocol, market sector, or technical topic to brief."},"focus":{"type":"string","description":"Analytical angle applied to the brief; defaults to 'technical_and_market_catalysts' when omitted.","enum":["technical_and_market_catalysts","security_incidents","regulatory_and_macro"]}},"required":["topic"]}` ### infer_mpp_streaming_session — Base EVM Machine Payments Protocol (MPP) Streaming Session Planner - Description: Initializes a Base USDC Machine Payments Protocol (MPP) metered inference session, allocating a streaming token quota and returning a step-by-step execution plan. Use when running session-metered agent planning settled via Base EVM MPP 'Payment-Challenge' headers; for mapping a task goal to L402 MCP tool calls without opening an MPP streaming session, use route_mcp_workflow_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'task' ('token_quota_tier' defaults to 'compact_1024'), supports '?demo=true' or MPP (100 sats), and returns HTTP 400 if invalid. - Required Parameters: task - Input Schema: `{"type":"object","properties":{"task":{"type":"string","description":"Agent workflow task to execute within the metered MPP session."},"token_quota_tier":{"type":"string","description":"Allocated streaming token ceiling for the session; defaults to 'standard_4096' when omitted.","enum":["compact_1024","standard_4096","extended_16384"]}},"required":["task"]}` ### generate_x402_vector_embeddings — Solana x402 USDC-Settled Semantic Vector Embedding Generator - Description: Generates normalized high-dimensional semantic vector embeddings settled via Solana SPL USDC ('x402' protocol headers) for decentralized RAG pipelines. Use when computing text embeddings paid via Solana USDC x402 signatures rather than Bitcoin Lightning; for extracting discrete JSON entities from unstructured text, use extract_structured_json_entities instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('encoding_format' defaults to 'float_array'), supports '?demo=true' or x402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: text - Input Schema: `{"type":"object","properties":{"text":{"type":"string","description":"Input text string or document chunk to convert into a normalized embedding vector."},"encoding_format":{"type":"string","description":"Vector serialization format; defaults to 'float_array' when omitted.","enum":["float_array","base64_float32"]}},"required":["text"]}` ### extract_clean_markdown — Web HTML to Clean LLM-Optimized Markdown Engine - Description: Converts raw HTML pages into clean, boilerplate-free, LLM-optimized Markdown with preserved hyperlinks and headings. Use when ingesting raw web documents or blog posts into agent context windows; for isolating tabular data into structured datasets, use parse_html_tables instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('conversion_mode' defaults to 'clean_semantic_article'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Raw HTML string of the web page or document to convert to clean Markdown."},"conversion_mode":{"type":"string","description":"Markdown extraction strategy: clean semantic article, preserve tables/code, or minimal text.","enum":["clean_semantic_article","preserve_tables_and_code","minimal_text_only"]},"preserve_links":{"type":"boolean","description":"Whether to retain anchor hyperlinks and image markdown references in output."}},"required":["html_content"]}` ### scrape_readable_article — Readability Article Body & Byline Extractor - Description: Extracts primary article body, author bylines, publication timestamps, and estimated reading duration from web pages. Use when stripping navigation bars, advertisement containers, and cookie banners to isolate core editorial content; for converting full HTML to markdown, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('readability_profile' defaults to 'article_body_strict'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Target web page HTML containing the article, editorial post, or blog content."},"readability_profile":{"type":"string","description":"Content isolation heuristic: strict article body, technical documentation, or forum thread.","enum":["article_body_strict","technical_docs","forum_discussion"]},"include_byline":{"type":"boolean","description":"Whether to parse author names, affiliations, and editorial publication dates."}},"required":["html_content"]}` ### extract_structured_metadata — OpenGraph, Twitter Cards & JSON-LD Microdata Extractor - Description: Extracts OpenGraph tags, Twitter Card metadata, canonical URLs, and Schema.org JSON-LD microdata scripts from HTML. Use when indexing social share cards, author identity, breadcrumbs, and rich snippet schemas for AI search agents; for scanning page hyperlinks and outbound references, use extract_page_hyperlinks instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('metadata_targets' defaults to 'all_protocols'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Source HTML string containing head tags, OpenGraph meta properties, or JSON-LD scripts."},"metadata_targets":{"type":"string","description":"Target metadata protocol filter: all protocols, OpenGraph and Twitter, or Schema.org JSON-LD.","enum":["all_protocols","opengraph_and_twitter","schema_org_json_ld"]},"include_favicons":{"type":"boolean","description":"Whether to extract favicon links and Apple Touch icon references."}},"required":["html_content"]}` ### parse_html_tables — HTML Table to Structured JSON & Markdown Parser - Description: Detects and parses HTML table elements into structured JSON record arrays and GitHub-Flavored Markdown tabular grids. Use when converting financial statements, product comparison grids, or sports statistics into structured data tables; for extracting raw clean markdown prose, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('output_format' defaults to 'markdown_and_json'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Raw HTML string containing one or more table, thead, tbody, or tr elements."},"output_format":{"type":"string","description":"Tabular export formatting standard: markdown and JSON, JSON records only, or CSV string.","enum":["markdown_and_json","json_records_only","csv_string"]},"min_rows":{"type":"integer","description":"Minimum rows required for a table to be parsed and retained."}},"required":["html_content"]}` ### isolate_css_selectors — Deterministic Edge DOM CSS Selector Scraper & Isolator - Description: Evaluates CSS selector queries against HTML DOM trees to extract targeted inner text, outer HTML, or element attributes. Use when targeting specific elements like pricing badges, product titles, review cards, or navigation breadcrumbs; for parsing unstructured contact information, use extract_contact_info instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' and 'selector_query' ('extraction_mode' defaults to 'inner_text'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content, selector_query - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"HTML source markup to query against using CSS selector matching rules."},"selector_query":{"type":"string","description":"CSS selector query expression (e.g., '.pricing-card', '#main h2', 'article p')."},"extraction_mode":{"type":"string","description":"DOM extraction representation: text content, outer HTML snippet, or attribute key-value map.","enum":["inner_text","outer_html","attribute_map"]}},"required":["html_content","selector_query"]}` ### detect_paywall_and_bypass — DOM Paywall, Modal Gate & Blurred Content Recovery Auditor - Description: Audits web page DOM hierarchies to detect soft paywalls, blur overlays, modal gates, and recovers concealed body text. Use when diagnosing paywall obstructions, diagnosing subscriber gating scripts, or auditing content access barriers; for assessing general SEO hygiene, use evaluate_seo_diagnostics instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('detection_profile' defaults to 'heuristic_dom_overlay'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Target web page HTML markup suspected of containing soft paywalls or paywall modals."},"detection_profile":{"type":"string","description":"Paywall detection heuristic: heuristic DOM overlay, hidden text recovery, or strict access barrier audit.","enum":["heuristic_dom_overlay","hidden_text_recovery","strict_audit"]},"target_domain":{"type":"string","description":"Optional publishing domain name to look up publisher gating patterns."}},"required":["html_content"]}` ### crawl_sitemap_urls — XML Sitemap & Index Crawler Tree Decompiler - Description: Parses XML sitemaps and sitemap index files into structured URL trees with change frequency and last-modified filters. Use when discovering domain architectures, mapping crawl frontiers, or indexing blog/product catalogues; for extracting on-page hyperlinks from raw HTML, use extract_page_hyperlinks instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sitemap_xml' ('filter_criteria' defaults to 'all_entries'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: sitemap_xml - Input Schema: `{"type":"object","properties":{"sitemap_xml":{"type":"string","description":"XML string of the sitemap or sitemapindex file to inspect and parse."},"filter_criteria":{"type":"string","description":"URL retention filter: all entries, recently modified lastmod only, or HTML pages only.","enum":["all_entries","recent_lastmod_only","html_pages_only"]},"max_results":{"type":"integer","description":"Maximum number of URLs to extract and return in the catalog."}},"required":["sitemap_xml"]}` ### extract_page_hyperlinks — Web Hyperlink, Anchor & Asset Extraction Filter - Description: Extracts, normalizes, and filters internal and external hyperlinks, anchor texts, and downloadable asset targets from HTML. Use when building site crawlers, auditing broken links, or extracting reference citations; for isolating primary readable article narrative text, use scrape_readable_article instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('link_scope' defaults to 'all_links'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Source HTML string containing anchor tags, href attributes, and link targets."},"link_scope":{"type":"string","description":"Link extraction scope: all links, internal domain only, external links only, or download assets.","enum":["all_links","internal_only","external_only","download_assets_only"]},"base_url":{"type":"string","description":"Base URL of the target page for resolving relative link paths."}},"required":["html_content"]}` ### sanitize_html_content — Edge HTML Sanitizer, Script Stripper & XSS Neutralizer - Description: Sanitizes raw HTML by removing malicious script tags, iframes, inline event handlers, and data URIs into safe markup. Use when preparing untrusted third-party web content for rendering in agent dashboards or email clients; for converting clean HTML into markdown, use extract_clean_markdown instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('sanitization_strictness' defaults to 'strip_scripts_and_iframes'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Untrusted or potentially hazardous HTML string requiring sanitization."},"sanitization_strictness":{"type":"string","description":"Sanitizer filter policy: strip scripts and iframes, allowlist safe formatting, or plaintext strip all.","enum":["strip_scripts_and_iframes","allowlist_safe_formatting","plaintext_strip_all"]},"preserve_images":{"type":"boolean","description":"Whether to retain safe img elements with http/https sources."}},"required":["html_content"]}` ### extract_contact_info — Lead Contact, Email, Phone & Social Handle Extractor - Description: Extracts email addresses, telephone numbers, physical addresses, and social network handles from web text and DOM footers. Use when researching sales leads, aggregating business contact directories, or extracting customer service info; for parsing structured tabular data, use parse_html_tables instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'content' ('extraction_focus' defaults to 'all_contacts'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: content - Input Schema: `{"type":"object","properties":{"content":{"type":"string","description":"Raw text or HTML page content to scan for contact channels and lead info."},"extraction_focus":{"type":"string","description":"Contact filter focus: all contact info, emails and phones only, or social handles only.","enum":["all_contacts","emails_and_phones_only","social_handles_only"]},"country_hint":{"type":"string","description":"Two-letter ISO country code for telephone numbering format hints."}},"required":["content"]}` ### evaluate_seo_diagnostics — Web SEO Diagnostics & Heading Hierarchy Auditor - Description: Audits HTML heading structures, title lengths, meta descriptions, image alt tags, and OpenGraph compliance into a health score. Use when auditing landing pages, verifying SEO compliance before publishing, or evaluating crawl friendliness; for extracting article bodies, use scrape_readable_article instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('audit_level' defaults to 'comprehensive_audit'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: html_content - Input Schema: `{"type":"object","properties":{"html_content":{"type":"string","description":"Web page HTML string to evaluate against search engine optimization standards."},"audit_level":{"type":"string","description":"Diagnostic audit scope: comprehensive audit, meta tags only, or heading hierarchy only.","enum":["comprehensive_audit","meta_tags_only","heading_hierarchy_only"]},"target_keyword":{"type":"string","description":"Primary search keyword to check for in titles, headings, and meta tags."}},"required":["html_content"]}` ### compile_rss_feed — Web Content to RSS 2.0 & Atom Feed Compiler - Description: Transforms JSON item collections or article card arrays into standardized RSS 2.0, Atom 1.0, or JSON Feed 1.1 syndication feeds. Use when syndicating blog articles, product announcements, or changelog cards to RSS readers and AI agents; for compiling structured sitemap listings, use crawl_sitemap_urls instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'items_json' and 'channel_title' ('feed_standard' defaults to 'rss_2_0'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: items_json, channel_title - Input Schema: `{"type":"object","properties":{"items_json":{"type":"string","description":"JSON string representing an array of article or feed items with title, link, and pubDate."},"channel_title":{"type":"string","description":"Headline title for the syndication feed channel."},"feed_standard":{"type":"string","description":"Target syndication feed specification: RSS 2.0, Atom 1.0, or JSON Feed 1.1.","enum":["rss_2_0","atom_1_0","json_feed_1_1"]}},"required":["items_json","channel_title"]}` ### synthesize_neural_search — Neural Search Synthesizer & Multi-Domain Ranker - Description: Executes multi-domain semantic search query expansion, relevance re-ranking, and extractive factual snippet bundling. Use when retrieving grounded web knowledge, evaluating search results across diverse domains, and retrieving cited answers; for building deep research briefings, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'search_query' ('search_mode' defaults to 'hybrid_semantic_keyword'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: search_query - Input Schema: `{"type":"object","properties":{"search_query":{"type":"string","description":"Primary search query, factual question, or technical topic to search."},"search_mode":{"type":"string","description":"Information retrieval strategy: hybrid semantic keyword, strict fact retrieval, or deep research.","enum":["hybrid_semantic_keyword","strict_fact_retrieval","deep_research"]},"max_results":{"type":"integer","description":"Maximum number of ranked result snippets to synthesize."}},"required":["search_query"]}` ### compile_research_dossier — Deep Research Dossier & Citation Intelligence Brief - Description: Compiles multi-source factual research briefs with verified citations, confidence intervals, and key analytical takeaways. Use when synthesizing comprehensive intelligence briefings on complex technical, scientific, or market developments; for rapid query search snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'research_topic' ('depth_level' defaults to 'executive_brief'), supports '?demo=true' or L402 (35 sats), and returns HTTP 400 if invalid. - Required Parameters: research_topic - Input Schema: `{"type":"object","properties":{"research_topic":{"type":"string","description":"Complex subject, market sector, emerging technology, or policy topic to research."},"depth_level":{"type":"string","description":"Research dossier rigor: executive brief, deep investigation, or technical whitepaper.","enum":["executive_brief","deep_investigation","technical_whitepaper"]},"target_citations":{"type":"integer","description":"Target number of primary citations to identify and verify."}},"required":["research_topic"]}` ### expand_search_queries — High-Entropy Boolean & Semantic Search Query Expander - Description: Generates targeted Boolean queries, semantic synonym variations, and sub-question expansions from an ambiguous prompt. Use when overcoming query vocabulary mismatches and expanding search recall across academic, code, or patent databases; for scoping queries to domain categories, use filter_domain_intelligence instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'base_query' ('expansion_strategy' defaults to 'boolean_operators'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: base_query - Input Schema: `{"type":"object","properties":{"base_query":{"type":"string","description":"Initial search prompt or ambiguous question requiring semantic query expansion."},"expansion_strategy":{"type":"string","description":"Query expansion method: Boolean operators, semantic synonyms, or cross-domain questions.","enum":["boolean_operators","semantic_synonyms","cross_domain_questions"]},"target_count":{"type":"integer","description":"Target count of query variations to synthesize."}},"required":["base_query"]}` ### filter_domain_intelligence — Curated Domain Registry Scope & Source Authority Filter - Description: Scopes search execution and filters results strictly across verified high-reputation domain registries and regulatory bodies. Use when restricting search discovery to verified academic papers, SEC filings, official documentation, or legal statutes; for checking specific factual claims, use verify_factual_claims instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query' ('domain_tier' defaults to 'academic_and_research'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: query - Input Schema: `{"type":"object","properties":{"query":{"type":"string","description":"Topic or query to execute across specialized domain registries."},"domain_tier":{"type":"string","description":"Curated domain authority tier: academic and research, regulatory and legal, tech docs, or financial.","enum":["academic_and_research","regulatory_and_legal","tech_documentation","financial_and_sec"]},"time_horizon":{"type":"string","description":"Optional recency filter window (e.g., '1y', '5y', 'all_time')."}},"required":["query"]}` ### analyze_news_recency — Real-Time News Recency, Trending Story Clusters & Velocity Tracker - Description: Tracks breaking news feeds, clusters trending story cycles, and calculates story publication velocity over recent timeframes. Use when analyzing breaking market catalysts, emerging controversies, or ongoing product announcements; for evaluating sentiment polarity across media, use analyze_media_sentiment instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'topic' ('recency_window' defaults to 'past_24_hours'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: topic - Input Schema: `{"type":"object","properties":{"topic":{"type":"string","description":"Subject, ticker symbol, brand, or public event to scan for breaking news developments."},"recency_window":{"type":"string","description":"News timestamp search window: past hour, past 24 hours, past 7 days, or past 30 days.","enum":["past_hour","past_24_hours","past_7_days","past_30_days"]},"sentiment_cluster":{"type":"boolean","description":"Whether to calculate sentiment direction across news story clusters."}},"required":["topic"]}` ### verify_factual_claims — Fact Verification & Consensus Evidence Evaluator - Description: Audits factual statements against authoritative consensus sources and assigns truthfulness scores with counter-evidence. Use when checking disputed claims, detecting AI hallucinations, or validating quotes before citation; for formatting academic citations, use extract_scholarly_citations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim_statement' ('verification_rigor' defaults to 'multi_source_consensus'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid. - Required Parameters: claim_statement - Input Schema: `{"type":"object","properties":{"claim_statement":{"type":"string","description":"Factual assertion, statistic, or quote requiring independent source verification."},"verification_rigor":{"type":"string","description":"Fact verification method: multi-source consensus, official records only, or probabilistic check.","enum":["multi_source_consensus","official_records_only","probabilistic_check"]},"context_domain":{"type":"string","description":"Optional domain context such as economics, medicine, history, or computer science."}},"required":["claim_statement"]}` ### extract_scholarly_citations — Scholarly Citation Compiler (BibTeX, APA, IEEE, MLA) & DOI Resolver - Description: Formats academic paper metadata and DOI identifiers into standard scholarly citation formats (BibTeX, APA, IEEE, MLA). Use when generating bibliographies for research papers, validating journal references, or resolving DOI identifiers; for structuring research timelines, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'source_content_or_doi' ('citation_style' defaults to 'bibtex_format'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: source_content_or_doi - Input Schema: `{"type":"object","properties":{"source_content_or_doi":{"type":"string","description":"DOI string, arXiv ID, or raw paper title with author list to format into citation."},"citation_style":{"type":"string","description":"Bibliographic citation standard: BibTeX format, APA 7th edition, IEEE standard, or MLA 9th edition.","enum":["bibtex_format","apa_7th_edition","ieee_standard","mla_9th_edition"]},"include_abstract":{"type":"boolean","description":"Whether to include publication abstract in structured metadata."}},"required":["source_content_or_doi"]}` ### cluster_topic_subgraphs — Semantic Topic Clustering & Subgraph Taxonomy Synthesizer - Description: Discovers latent thematic clusters, subtopic branches, and conceptual relationships across document corpora. Use when structuring broad search results into distinct thematic silos or generating table of contents taxonomies; for tracking chronological milestones, use summarize_temporal_timeline instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'documents_or_queries' ('clustering_method' defaults to 'tf_idf_semantic_graph'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: documents_or_queries - Input Schema: `{"type":"object","properties":{"documents_or_queries":{"type":"string","description":"Newline-separated list or JSON array of text snippets, queries, or article abstracts."},"clustering_method":{"type":"string","description":"Thematic clustering algorithm: TF-IDF semantic graph, centroid k-means, or hierarchical taxonomy.","enum":["tf_idf_semantic_graph","centroid_kmeans","hierarchical_taxonomy"]},"max_clusters":{"type":"integer","description":"Maximum number of thematic cluster groups to partition data into."}},"required":["documents_or_queries"]}` ### analyze_media_sentiment — Multi-Source Media Sentiment & Bull/Bear Polarity Oracle - Description: Evaluates brand, market, or topic sentiment across news headlines, discussions, and articles with bull/bear polarity scores. Use when assessing market sentiment, social brand perception, or controversy exposure on specific entities; for compiling competitive market comparisons, use compile_competitive_landscape instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text_or_headlines' ('sentiment_domain' defaults to 'general_news'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: text_or_headlines - Input Schema: `{"type":"object","properties":{"text_or_headlines":{"type":"string","description":"Collection of headlines, commentary strings, or editorial paragraphs to evaluate."},"sentiment_domain":{"type":"string","description":"Lexicon domain weighting: general news, financial markets, or developer ecosystem.","enum":["general_news","financial_markets","developer_ecosystem"]},"entity_filter":{"type":"string","description":"Optional specific brand, company, or coin name to isolate sentiment around."}},"required":["text_or_headlines"]}` ### rank_expert_sources — Domain Expert Authority Ranking & Primary Source Discovery - Description: Identifies and ranks top domain authorities, leading researchers, and primary documentation repositories for technical topics. Use when finding primary source experts to cite or discovering foundational documentation for specialized fields; for ranking general search query snippets, use synthesize_neural_search instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'subject_area' ('authority_metric' defaults to 'pagerank_and_domain_authority'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: subject_area - Input Schema: `{"type":"object","properties":{"subject_area":{"type":"string","description":"Academic field, open source framework, protocol, or technical discipline to explore."},"authority_metric":{"type":"string","description":"Reputation evaluation standard: PageRank and domain authority, citation h-index, or code repo stars.","enum":["pagerank_and_domain_authority","citation_h_index","code_repository_stars"]},"max_experts":{"type":"integer","description":"Maximum number of top domain authorities to return in the ranking."}},"required":["subject_area"]}` ### summarize_temporal_timeline — Chronological Event Timeline Compiler & Milestone Synthesizer - Description: Synthesizes chronological milestone timelines from search results, news archives, and historical documents. Use when reconstructing historical events, tracking company histories, or mapping regulatory progression; for tracking real-time breaking news in the past 24 hours, use analyze_news_recency instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'event_corpus' ('timeline_resolution' defaults to 'chronological_milestones'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: event_corpus - Input Schema: `{"type":"object","properties":{"event_corpus":{"type":"string","description":"Unstructured text corpus containing dated events, news reports, or historical accounts."},"timeline_resolution":{"type":"string","description":"Temporal event grouping: chronological milestones, daily chronicle, or weekly epochs.","enum":["chronological_milestones","daily_chronicle","weekly_epochs"]},"ascending_order":{"type":"boolean","description":"Whether to sort timeline from oldest to newest (true) or reverse chronological (false)."}},"required":["event_corpus"]}` ### compile_competitive_landscape — Competitor Intelligence, Feature Matrix & Moat Analyzer - Description: Compiles multi-competitor comparison matrices, pricing tiers, feature coverage, and strategic moat evaluations. Use when analyzing market landscapes, evaluating pricing parity, or conducting diligence on competing product offerings; for compiling narrative research briefs, use compile_research_dossier instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'target_entity_or_market' ('analysis_framework' defaults to 'feature_and_pricing_matrix'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid. - Required Parameters: target_entity_or_market - Input Schema: `{"type":"object","properties":{"target_entity_or_market":{"type":"string","description":"Industry sector, product category, or target company to benchmark against competitors."},"analysis_framework":{"type":"string","description":"Benchmarking framework: feature and pricing matrix, SWOT competitive moat, or market share quadrant.","enum":["feature_and_pricing_matrix","swot_competitive_moat","market_share_quadrant"]},"max_competitors":{"type":"integer","description":"Maximum number of market competitors to profile and contrast."}},"required":["target_entity_or_market"]}` ### synthesize_sql_query — Deterministic NL-to-SQL Synthesizer & Dialect Query Generator - Description: Translates natural language questions into dialect-accurate, optimized SQL SELECT queries with schema awareness and safety checks. Use when generating reporting queries or automated data analytics pipelines; for analyzing SQL execution performance and EXPLAIN plans, use analyze_query_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'natural_language_request' and 'schema_ddl' ('sql_dialect' defaults to 'postgresql_dialect'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: natural_language_request, schema_ddl - Input Schema: `{"type":"object","properties":{"natural_language_request":{"type":"string","description":"Natural language question or reporting requirement to transform into SQL."},"schema_ddl":{"type":"string","description":"Database schema DDL statements defining available tables, columns, and relations."},"sql_dialect":{"type":"string","description":"Target SQL dialect specification: PostgreSQL dialect, MySQL dialect, or SQLite dialect.","enum":["postgresql_dialect","mysql_dialect","sqlite_dialect"]},"read_only_mode":{"type":"boolean","description":"Whether to enforce strict read-only SELECT query constraints."}},"required":["natural_language_request","schema_ddl"]}` ### audit_sql_injection_ast — Deterministic SQL AST Injection & Tautology Vulnerability Auditor - Description: Statically parses SQL queries via AST lexical analysis to detect second-order injection, tautology conditions, and stacked queries. Use when auditing dynamic query parameters or untrusted user input before database execution; for sanitizing query strings for telemetry logging, use sanitize_sql_telemetry instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'raw_sql' ('audit_sensitivity' defaults to 'strict_zero_dynamic_taint'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: raw_sql - Input Schema: `{"type":"object","properties":{"raw_sql":{"type":"string","description":"Raw SQL query string to parse and audit for injection vulnerabilities."},"audit_sensitivity":{"type":"string","description":"Audit sensitivity mode: strict zero dynamic taint, second order injection check, or standard syntax audit.","enum":["strict_zero_dynamic_taint","second_order_injection_check","standard_syntax_audit"]},"allow_comments":{"type":"boolean","description":"Whether SQL inline comments are allowed or treated as injection vectors."}},"required":["raw_sql"]}` ### analyze_query_plan — SQL Query Plan EXPLAIN Optimizer & Bottleneck Diagnostics - Description: Analyzes SQL EXPLAIN execution plans to detect sequential table scans, high-cost cartesian joins, and buffer memory bottlenecks. Use when diagnosing slow queries, optimizing database performance, or evaluating query cost; for getting index recommendations, use recommend_database_indexes instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'explain_plan_or_query' ('optimization_target' defaults to 'eliminate_seq_scans'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: explain_plan_or_query - Input Schema: `{"type":"object","properties":{"explain_plan_or_query":{"type":"string","description":"Raw text or JSON output of EXPLAIN / EXPLAIN ANALYZE or the candidate SQL query."},"optimization_target":{"type":"string","description":"Optimization goal: eliminate sequential scans, reduce memory buffers, or minimize join costs.","enum":["eliminate_seq_scans","reduce_memory_buffers","minimize_join_costs"]},"database_engine":{"type":"string","description":"Database engine name (e.g., 'postgres', 'mysql', 'sqlite')."}},"required":["explain_plan_or_query"]}` ### detect_breaking_migrations — Database Schema Migration Differ & Breaking Change Linter - Description: Compares source and target DDL schemas to identify breaking changes, destructive column drops, and lock-inducing mutations. Use when verifying CI/CD migration scripts before production deployment to prevent downtime; for verifying relational normal form, use validate_schema_normalization instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'current_schema' and 'target_schema' ('risk_tolerance' defaults to 'zero_downtime_strict'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: current_schema, target_schema - Input Schema: `{"type":"object","properties":{"current_schema":{"type":"string","description":"Current production database DDL schema representing live tables and columns."},"target_schema":{"type":"string","description":"Proposed new database DDL schema representing target migration state."},"risk_tolerance":{"type":"string","description":"Deployment safety policy: zero downtime strict, allow transient locks, or permissive dev.","enum":["zero_downtime_strict","allow_transient_locks","permissive_dev"]}},"required":["current_schema","target_schema"]}` ### transpile_sql_dialect — Polyglot SQL Dialect Transpiler (PostgreSQL, MySQL, SQLite) - Description: Transpiles SQL queries and DDL schemas across PostgreSQL, MySQL, and SQLite dialects, rewriting functions and syntax quirks. Use when migrating application queries across database backends or testing against in-memory SQLite; for generating new queries from natural language, use synthesize_sql_query instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_code' and 'source_dialect' ('target_dialect' defaults to 'sqlite'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: sql_code, source_dialect, target_dialect - Input Schema: `{"type":"object","properties":{"sql_code":{"type":"string","description":"SQL query or DDL statement to convert from source dialect into target dialect."},"source_dialect":{"type":"string","description":"Original SQL dialect of the input code: postgresql, mysql, or sqlite.","enum":["postgresql","mysql","sqlite"]},"target_dialect":{"type":"string","description":"Destination SQL dialect to transpile into: postgresql, mysql, or sqlite.","enum":["postgresql","mysql","sqlite"]}},"required":["sql_code","source_dialect","target_dialect"]}` ### recommend_database_indexes — Database Index Advisor & Composite B-Tree Optimizer - Description: Recommends optimal single-column and composite B-Tree/BRIN indexes based on slow query WHERE, JOIN, and ORDER BY clauses. Use when optimizing database response times and eliminating full-table scans; for inspecting full execution plans, use analyze_query_plan instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'slow_queries_or_workload' ('index_type_preference' defaults to 'btree_and_composite'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: slow_queries_or_workload - Input Schema: `{"type":"object","properties":{"slow_queries_or_workload":{"type":"string","description":"Collection of slow SQL queries or workload log statements to analyze for index gaps."},"index_type_preference":{"type":"string","description":"Target indexing strategy: B-tree and composite, BRIN and GIN sparse, or covering indexes with INCLUDE.","enum":["btree_and_composite","brin_and_gin_sparse","covering_indexes_include"]},"max_new_indexes":{"type":"integer","description":"Maximum number of index creation statements to recommend."}},"required":["slow_queries_or_workload"]}` ### validate_schema_normalization — Relational Schema Normalization Auditor (3NF, BCNF) & Integrity Guard - Description: Audits database schemas for third normal form (3NF) compliance, transitive dependencies, and missing foreign key constraints. Use when reviewing database architectures, preventing update anomalies, or validating relational integrity; for detecting breaking schema migrations, use detect_breaking_migrations instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('target_normal_form' defaults to 'third_normal_form_3nf'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: schema_ddl - Input Schema: `{"type":"object","properties":{"schema_ddl":{"type":"string","description":"Database schema DDL statements defining table columns, primary keys, and relations."},"target_normal_form":{"type":"string","description":"Target normalization standard: 3NF, Boyce-Codd BCNF, or denormalized OLAP star.","enum":["third_normal_form_3nf","boyce_codd_bcnf","denormalized_olap_star"]},"strict_keys":{"type":"boolean","description":"Whether to enforce explicit foreign key constraints on all ID references."}},"required":["schema_ddl"]}` ### sanitize_sql_telemetry — SQL Query Telemetry PII Scrubber & Parameterization Masker - Description: Masks PII, financial values, and credential literals from raw SQL query logs and slow-query dumps before telemetry storage. Use when scrubbing production database query logs before shipping to APM tools, Datadog, or external log collectors; for auditing SQL injection vulnerabilities, use audit_sql_injection_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'query_logs' ('masking_policy' defaults to 'mask_pii_and_literals'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: query_logs - Input Schema: `{"type":"object","properties":{"query_logs":{"type":"string","description":"Raw SQL query text or multi-line database query log strings requiring sanitization."},"masking_policy":{"type":"string","description":"Scrubbing rigor policy: mask PII and literals, anonymize all constants, or strict AST parameterization.","enum":["mask_pii_and_literals","anonymize_all_constants","strict_ast_parameterization"]},"hash_salt":{"type":"string","description":"Optional salt string for deterministic pseudonymization of user IDs."}},"required":["query_logs"]}` ### synthesize_seed_fixtures — Deterministic Relational Seed Data & SQL Mock Fixture Generator - Description: Generates deterministic relational test seed fixtures respecting foreign key constraints, unique indexes, and data bounds. Use when provisioning mock database datasets for automated testing, staging environments, or sandbox demos; for compiling ORM models from schemas, use generate_orm_models instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('fixture_volume' defaults to 'minimal_smoke_test_5'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: schema_ddl - Input Schema: `{"type":"object","properties":{"schema_ddl":{"type":"string","description":"Target database schema DDL defining tables, column types, and foreign key relations."},"fixture_volume":{"type":"string","description":"Mock dataset volume profile: minimal smoke test (5), standard dataset (50), or stress dataset (500).","enum":["minimal_smoke_test_5","standard_dataset_50","stress_dataset_500"]},"deterministic_seed":{"type":"integer","description":"Integer seed for reproducible pseudo-random data generation."}},"required":["schema_ddl"]}` ### calculate_pool_headroom — Database Connection Pool Sizing & Concurrency Headroom Calculator - Description: Calculates optimal connection pool sizing, idle timeouts, and client headroom based on server RAM and concurrency profile. Use when sizing PgBouncer, HikariCP, or Prisma connection pools to avoid server out-of-memory crashes; for checking transaction isolation hazards, use audit_transaction_isolation instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'server_ram_mb' and 'max_concurrent_clients' ('workload_profile' defaults to 'high_concurrency_oltp'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid. - Required Parameters: server_ram_mb, max_concurrent_clients - Input Schema: `{"type":"object","properties":{"server_ram_mb":{"type":"number","description":"Total available RAM in megabytes dedicated to the database server instance."},"max_concurrent_clients":{"type":"number","description":"Peak anticipated concurrent client connections or serverless worker threads."},"workload_profile":{"type":"string","description":"Workload operational characteristics: high-concurrency OLTP, heavy analytical OLAP, or serverless edge burst.","enum":["high_concurrency_oltp","heavy_analytical_olap","serverless_edge_burst"]}},"required":["server_ram_mb","max_concurrent_clients"]}` ### audit_transaction_isolation — Transaction Concurrency Anomaly & Isolation Level Hazard Auditor - Description: Audits database transaction workflows for concurrency anomalies, dirty reads, non-repeatable reads, and deadlock risks. Use when reviewing financial transfer procedures, inventory decrement operations, or multi-step checkout workflows; for calculating connection pool headroom, use calculate_pool_headroom instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'transaction_steps' ('target_isolation_level' defaults to 'read_committed'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: transaction_steps - Input Schema: `{"type":"object","properties":{"transaction_steps":{"type":"string","description":"Sequential SQL commands or description of business operations within the transaction."},"target_isolation_level":{"type":"string","description":"Candidate SQL isolation level: read committed, repeatable read, or serializable.","enum":["read_committed","repeatable_read","serializable"]},"strict_deadlock_check":{"type":"boolean","description":"Whether to perform exhaustive cross-table lock acquisition ordering analysis."}},"required":["transaction_steps"]}` ### generate_orm_models — SQL DDL to Type-Safe ORM Entity Compiler (Prisma, Drizzle, Zod) - Description: Compiles SQL DDL schemas into type-safe ORM entities and TypeScript validation schemas (Prisma, Drizzle, SQLAlchemy, Zod). Use when scaffolding application models, generating TypeScript data layers, or synchronizing schemas; for translating raw SQL across dialects, use transpile_sql_dialect instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'schema_ddl' ('orm_target' defaults to 'drizzle_orm_typescript'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid. - Required Parameters: schema_ddl - Input Schema: `{"type":"object","properties":{"schema_ddl":{"type":"string","description":"Database schema DDL statements defining tables, primary keys, and relationships."},"orm_target":{"type":"string","description":"Target ORM framework standard: Prisma schema, Drizzle ORM TypeScript, SQLAlchemy Python 2.0, or Zod types.","enum":["prisma_schema","drizzle_orm_typescript","sqlalchemy_python_2_0","zod_types_validation"]},"include_relations":{"type":"boolean","description":"Whether to generate explicit foreign key relation decorators and navigation properties."}},"required":["schema_ddl"]}`