AI Agent Audit and Action Review
Server Details
Second opinion for risky AI tool calls. Evidence, risks, and next steps for 1 EURC via x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
read_agent_action_review is clearly distinct (read-only retrieval by request ID), but get_agent_action_review_checkout and get_agent_action_review_service overlap: both are 'get' tools that surface setup/purchase information, and an agent may struggle to know which to call first. The descriptions do differentiate account/checkout from documentation, which keeps it from being worse.
All three tools use snake_case with a consistent verb_noun pattern and a shared 'agent_action_review' domain prefix (get_..._checkout, get_..._service, read_...). Minor looseness in using 'get' for two semantically different retrievals, but the convention is predictable.
Three tools is lean but reasonable for a narrow service: discover the offering, obtain a checkout/setup path, and read an existing report. Each tool has a distinct role, though the surface is close to thin.
The core action—submitting/purchasing a review—is explicitly not a tool ('purchased separately via POST /v1/review'), so the agent must fall back to raw HTTP for the primary workflow. There is also no tool to check the status of a pending review, leaving a significant lifecycle gap.
Available Tools
3 toolsget_agent_action_review_checkoutCheck checkout for a 1 EURC agent action reviewARead-onlyInspect
Check the EURC account and get the checkout URL. If setup is required, optionally supply a public payer address and an explicitly authorized SOL budget to receive an unsigned setup transaction. This tool never signs, broadcasts or charges anything. A review is purchased separately via POST /v1/review.
Inputs: setup.
get_agent_action_review_serviceAI agent audit and preflight risk assessmentARead-onlyInspect
Find out how to get a 1 EURC second opinion before executing risky tool calls such as deleting files, publishing content, sending email or changing access. Returns an example, the purchase endpoint and the optional first-time setup path.
Inputs: no named parameters.
read_agent_action_reviewRead a previously paid agent action reviewARead-onlyInspect
Retrieve an existing report using the original private request ID. This tool is read-only and creates no new purchase.
Inputs: request_id (required). Returns: kind, model, summary, verdict, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Smart-contract risk reports for AI agents on 20 EVM chains, paid per call via x402 ($0.02 USDC).
AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.
Pay-per-call checks for AI agents: sanctions, MiCA, French KYB, AI Act. USDC via x402.
Related MCP Servers
- FlicenseAqualityCmaintenanceAgent-Level Transaction Safety Oracle. Before an AI agent signs a blockchain transaction, it returns a SAFE/UNSAFE verdict with a SENTINEL Score (AAA-D) and risk flags. Pay-per-call $0.005 USDC via x402 on Base.1-
- AlicenseNot gradedqualityDmaintenanceAdversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.MIT

thoughtproof-mcpofficial
AlicenseCqualityBmaintenanceAdversarial multi-model reasoning verification for AI agents. Claude, Grok, and DeepSeek challenge each decision — returns ALLOW or HOLD with JWKS-signed attestation. x402-gated on Base.561 npm1MIT- AlicenseNot gradedqualityBmaintenancePay-per-call checks an AI agent runs before it moves money: token safety verdicts and wallet risk profiles on Base, on-chain payment verification, IBAN/VAT/BIC/LEI/ISIN validation, and live TLS and email-spoofing posture for a domain. Paid in USDC over x402 with no API key or account; the free payment_info tool explains the pricing.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.