AI Agent Audit and Action Review MCP server
dev.workers.michigkchatgpt.agent-action-review/agent-action-reviewagent-action-review.michigkchatgpt.workers.devstreamable-httpv1.0.10Scanned
Free samples. Buy a second opinion on risky AI actions for 1 EUR in SOL or EURC.
5 tools: 1 do something that can't be undone and 4 only read.
- Reads private data · 1
- Reads text others write · 5
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the AI Agent Audit and Action Review MCP server can do
The AI Agent Audit and Action Review MCP server is published by agent-action-review.michigkchatgpt.workers.dev, a domain the MCP Registry verified. It has 5 tools. It can do things that cannot be undone, such as sending, paying or publishing (purchase_agent_action_review), but cannot delete data. 4 tools only read.
1 tool reads private data (get_agent_action_review_service); 5 tools bring in text other people can write (get_agent_action_review_service, get_agent_action_review_example, read_agent_action_review and 2 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 22, 2026, version 1.0.10.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Can't be undone 1Claude Code: ask
purchase_agent_action_reviewGet an unsigned Solana transaction for one risk review.Reads text others writeNo findings
Why it is in this group
- The name "purchase_agent_action_review" says "purchase": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get an unsigned Solana transaction for one risk review. Choose asset SOL to pay the €1 equivalent without token account setup, or EURC to pay 1 EURC. Provide your public payer address and approved total SOL budget. After your wallet signs and sends it, call this tool with the same request ID and review and the finalized transaction_signature to receive the report.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
get_agent_action_review_checkoutFind checkout options for a 1 EURC report.Reads text others writeNo findings
Why it is in this group
- The name "get_agent_action_review_checkout" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "get_agent_action_review_checkout" says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Find checkout options for a 1 EURC report. Direct Solana checkout combines the purchase and any required account setup in one buyer-signed transaction. The x402 route is also listed. This tool can prepare a setup-only draft with an authorized budget and never signs, broadcasts or charges anything.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
get_agent_action_review_exampleRead a complete sample report for a bulk deletion, an overly broad access grant, or an unverified publication.Reads text others writeNo findings
Why it is in this group
- The name "get_agent_action_review_example" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_agent_action_review_example" says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Read a complete sample report for a bulk deletion, an overly broad access grant, or an unverified publication. Returns the sample input, verdict, evidence, risks and next steps. No wallet, payment or private data needed.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_agent_action_review_serviceFind 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.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_agent_action_review_service" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "find" and "file": it reads files.
- untrusted-inputThe name "get_agent_action_review_service" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "find" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
read_agent_action_reviewRetrieve an existing report using the original private request ID.Reads text others writeNo findings
Why it is in this group
- The name "read_agent_action_review" says "read": a word for reading.
What it can reach
- untrusted-inputThe name "read_agent_action_review" says "read" and "review": it reads comments, which other people can write.
Description, as the server wrote it Retrieve an existing report using the original private request ID. This tool is read-only and creates no new purchase.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:19 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:get_agent_action_review_exampleOnly reads
- Changed:purchase_agent_action_reviewCan't be undonetitledescriptioninputSchema
Tools1 added.+1 addedView diff
- Added:purchase_agent_action_reviewCan't be undone
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:get_agent_action_review_checkoutOnly reads
- Changed:get_agent_action_review_serviceOnly readstitledescription
Install
Pinned to version 1.0.10. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-action-review https://agent-action-review.michigkchatgpt.workers.dev/mcpclaude mcp add --transport http agent-action-review https://agent-action-review.michigkchatgpt.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agent-action-review__get_agent_action_review_service",
"mcp__agent-action-review__get_agent_action_review_example",
"mcp__agent-action-review__read_agent_action_review",
"mcp__agent-action-review__get_agent_action_review_checkout"
],
"ask": [
"mcp__agent-action-review__purchase_agent_action_review"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-action-review. Review it before you use it.
Capability tags behind 5 rules
- mcp__agent-action-review__get_agent_action_review_service private-data, untrusted-input
- mcp__agent-action-review__get_agent_action_review_example untrusted-input
- mcp__agent-action-review__read_agent_action_review untrusted-input
- mcp__agent-action-review__get_agent_action_review_checkout untrusted-input
- mcp__agent-action-review__purchase_agent_action_review untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.workers.michigkchatgpt.agent-action-review/agent-action-review/verify?hash=c687a197ae52bd20c35e069be0b923054ff9e410629a66a95ba8dbda90414f59" | jq -e '.changed == false'Pinned hash c687a197ae52, from Nov 22, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.michigkchatgpt.agent-action-review/agent-action-review/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.michigkchatgpt.agent-action-review/agent-action-review)Source: MCP Registry. Synced Nov 22, 2026, 03:17 UTC.
AI Agent Audit and Action Review MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AI Agent Audit and Action Review MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AI Agent Audit and Action Review MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AI Agent Audit and Action Review MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: purchase_agent_action_review.
What tools does the AI Agent Audit and Action Review MCP server have?
- 5 tools: 1 irreversible, 4 read. purchase_agent_action_review, get_agent_action_review_service, get_agent_action_review_example, read_agent_action_review and get_agent_action_review_checkout.
Does the AI Agent Audit and Action Review MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AI Agent Audit and Action Review MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AI Agent Audit and Action Review MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 22, 2026. Every change is on this page and in its Atom feed.