AI Agent Audit and Action Review
Second opinion for risky AI tool calls. Evidence, risks, and next steps for 1 EURC via x402.
Description as published in the official MCP registry.
Maintain this server? Get the badge
What we measured
| Endpoint | https://agent-action-review.michigkchatgpt.workers.dev/mcp | registry |
|---|---|---|
| Website | agent-action-review.michigkchatgpt.workers.dev/en | registry |
| Handshake | Answers the MCP handshake and lists its tools (153 ms) | our check, 2026-11-21 |
| Protocol version | 2026-07-28 | our check, 2026-11-21 |
| Tools (3) | get_agent_action_review_service, read_agent_action_review, get_agent_action_review_checkout | tools/list, 2026-11-21 |
| Registry version | 1.0.6 · active · updated 2026-11-21 | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows that the gate allowed a call, not just an opinion; it does not prove which server answered. How to file one.
Connect
claude mcp add --transport http agent-action-review https://agent-action-review.michigkchatgpt.workers.dev/mcpCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- Compaction-loss audit Compaction witness for agents: pin invariants, name dropped spans, re-inject verbatim or…
- Spree Commerce developer docs for AI agents Spree Commerce docs for AI coding agents: build headless B2B and marketplace ecommerce on…
- COTAL actions (cotal.ai) cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist…
- Skill Audit — Security Scanner for MCP Servers & Agent Skills MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack…
- Actionbook Let your AI agent operate any website through a real, logged-in browser session.
- AgentRQ Task manager for AI agents. Orchestrate agents to achieve large goals in unified control…
Is this your server?
Show the result of our latest check where your users look first. The badge is a live image: it changes when our check does, and it links back to this page.
[](https://openforallofus.com/tools/dev.workers.michigkchatgpt.agent-action-review/agent-action-review)<a href="https://openforallofus.com/tools/dev.workers.michigkchatgpt.agent-action-review/agent-action-review"><img src="https://openforallofus.com/badge/dev.workers.michigkchatgpt.agent-action-review/agent-action-review.svg" alt="Agora: MCP handshake check" height="20"></a>The badge reports one thing: the result of our last handshake check. A server with no remote endpoint shows as "runs locally". How we check.
Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name dev.workers.michigkchatgpt.agent-action-review/agent-action-review.