AI Agent Security Audit MCP Server

by workers-manhliemcn4euwlu-llmrt-companion Your server? Claim it

answering

AI Agent Security Audit is answering right now. Last checked 16 min ago. It exposes 5 tools.

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

Uptime history 7 hours of history · worst hour 75%

7 hours agonow

95.7%

Uptime 24h

22 of 23 checks

Tools

read from the server

1977 ms

Response time

average over 24h

open, no key

Access

streamable-http

AI Agent Security Audit does not always answer

Over the last week it answered 95.7% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 16 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit

~/.codex/config.toml

[mcp_servers.mcp-audit]
url = "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-audit": {
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "mcp-audit": {
      "type": "http",
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

free

run_free_scan

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.

pricing

get_pricing

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.

purchase

get_purchase_flow

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).

scan

get_scan_result

Poll a scan by job id (returned by run_free_scan) until status=done.

validate

validate

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.

Endpoints

URL	Transport	State	Latency	Checked
https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit	streamable-http	answering	4359 ms	16 min ago

Alternatives to AI Agent Security Audit

same job, measured the same way

LLM Red-Team Scanner

by manhliemcn4euwlu-source

LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails

5 tools answering

LLM Security Scanner

by workers-manhliemcn4euwlu-llmrt-companion

LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.

5 tools answering

LLM Security Scanner: Red-Team, Jailbreak, Prompt Injection Audit

by workers-manhliemcn4euwlu-llmrt-companion

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

5 tools answering

Agentpay Sentinel MCP

by rumblingb

Security guardrails for AI agent payments

local only

Guardrails

by expertvagabond

AI Agent Guardrails MCP server - security layer

77 installs/wk local only

Release Gate

by vamsisudhakaran1

Pre-deploy security auditor for AI agent code — the risks generic SAST misses.

222 installs/wk local only

Pageaudit

by pageaudit

Technical SEO, passive security and page-delivery audits with evidence and suggested fixes.

62 tools answering

MCP Audit Server

by joepangallo

Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend

77 installs/wk local only

AI Agent Security Audit — questions

Answers built from our own checks of this server.

What can AI Agent Security Audit do?

It exposes 5 tools, read directly from the server on our last check. Among them: get_pricing, get_purchase_flow, get_scan_result, run_free_scan, validate. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is AI Agent Security Audit working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 22 of 23 checks got a reply (95.7%), average response time 1977 ms. The bar chart above shows every period we have measured.

How do I connect AI Agent Security Audit?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does AI Agent Security Audit need an API key?

No. AI Agent Security Audit completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.