Skip to content

AI Agent Security Audit MCP server

dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-auditllmrt-companion.manhliemcn4euwlu.workers.devstreamable-httpv1.1.0Scanned

AI agent security audit: red-team probes plus missing-guardrail review with fixes.

5 tools: 1 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 1 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Sign-in required, no OAuth metadata. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Security Audit MCP server can do

The AI Agent Security Audit MCP server is published by llmrt-companion.manhliemcn4euwlu.workers.dev, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: run_free_scan), but cannot delete data. 4 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 17, 2026, version 1.1.0.

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

Changes things 1Claude Code: ask
  • run_free_scanFree LLM agent security review in ~35s.No findings

    Why it is in this group

    • The name "run_free_scan" says "run": a word for a change.
    Description, as the server wrote it
    Free LLM agent security review in ~35s. Two parts: (1) 8 live adversarial probes (jailbreak / prompt injection / system-prompt extraction / tool abuse) against your agent spec, and (2) a deterministic static audit of which guardrails the spec text itself is missing. Returns a 0-100 risk score, per-finding evidence, and a paste-ready guardrail sentence for each gap.
Only reads 4Show 4 read-only tools
  • get_pricingPRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card.No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    PRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card.
  • get_purchase_flowMachine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll…No findings

    Why it is in this group

    • The name "get_purchase_flow" says "get": a word for reading.
    Description, as the server wrote it
    Machine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll fallback).
  • get_scan_resultPoll a scan by job id (returned by run_free_scan) until status=done.No findings

    Why it is in this group

    • The name "get_scan_result" says "get": a word for reading.
    Description, as the server wrote it
    Poll a scan by job id (returned by run_free_scan) until status=done.
  • validateJudge one delivery against the task's own acceptance rule and return {verdict: accepted|rejected, reason}.No findings

    Why it is in this group

    • The name "validate" says "validate": a word for reading.
    Description, as the server wrote it
    Judge one delivery against the task's own acceptance rule and return {verdict: accepted|rejected, reason}. Called by the brick.blue hub when this seat is drawn as validator. Judges only machine-checkable criteria (json_schema / contains / fields); a task with no such rule is accepted, because rejecting needs evidence.

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 private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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.

Sign-in required, no OAuth metadata

Looked at Nov 18, 2026, 16:22 UTC, unchanged since Nov 11, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
530
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 530.

Posture changes

  1. Nov 11, 2026
    • HTTP status of an anonymous initialize: 200 to 530
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 530; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 530
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http audit https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit
claude mcp add --transport http audit https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__audit__get_scan_result",
      "mcp__audit__get_pricing",
      "mcp__audit__get_purchase_flow",
      "mcp__audit__validate"
    ],
    "ask": [
      "mcp__audit__run_free_scan"
    ],
    "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 audit. Review it before you use it.

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.manhliemcn4euwlu.llmrt-companion/mcp-audit/verify?hash=138ae063115e87d0ac5e7a33ded329700d9e6e69cad22ac5f9c69bc18222d112" | jq -e '.changed == false'

Pinned hash 138ae063115e, from Nov 17, 2026, 15:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-audit/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-audit
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-audit.svg)](https://radar.anlyon.com/servers/dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-audit)

Source: MCP Registry. Synced Nov 4, 2026, 00:18 UTC.

AI Agent Security Audit MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AI Agent Security Audit 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 Security Audit 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 Security Audit MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AI Agent Security Audit MCP server have?

5 tools: 1 write, 4 read. run_free_scan, get_scan_result, get_pricing, get_purchase_flow and validate.

Does the AI Agent Security Audit MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the AI Agent Security Audit 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 Security Audit MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.