Coding Agent Audit MCP Server

by stackscribe-ai Your server? Claim it

local only

Coding Agent Audit runs on your own machine — the client starts it, so there is no endpoint to ping. 2 656 installs a week from pypi. Last commit 1 Nov 2026.

Scans for known AI coding assistant supply-chain backdoors and risky Claude Code / MCP config.

Installs per day peak 1 739 · avg 88

a month agotoday

2 656

Installs / week

pypi · coding-agent-audit

Stars

0 open issues

1 Nov 2026

Last commit

from GitHub

—

License

Python

What the code does

We read the source, 22 h ago · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Opens a reverse shell src/agentaudit/configscan.py:27, [пакет] src/agentaudit/configscan.py:27

    (r"/dev/tcp/", "opens a raw bash TCP socket (common reverse-shell technique)"),

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/agentaudit/checks.py:252, [пакет] src/agentaudit/checks.py:252

        result = subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Coding Agent Audit and you get told the day something new turns up.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add coding-agent-audit -- uvx coding-agent-audit

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "coding-agent-audit": {
      "command": "uvx",
      "args": [
        "coding-agent-audit"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.coding-agent-audit]
command = "uvx"
args = ["coding-agent-audit"]

.cursor/mcp.json

{
  "mcpServers": {
    "coding-agent-audit": {
      "command": "uvx",
      "args": [
        "coding-agent-audit"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "coding-agent-audit": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "coding-agent-audit"
      ]
    }
  }
}

Alternatives to Coding Agent Audit

same job, measured the same way

Vectora

by brunosrz

AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.

56 installs/wk local only

Preflight

by newrelic-experimental

New Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)

1 614 installs/wk local only

Thinkrun

by dundas

Browser control + session recording MCP for AI coding agents (Claude Code, Cursor) — real Chrome.

93 installs/wk local only

Radzen Blazor MCP

by radzen-www

AI coding assistant for Radzen Blazor — docs, APIs, code samples, and templates for 100+ components.

answering

Valca

by pranlabs

Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.

78 installs/wk local only

Wcag Accessibility

by aditya-ariosity

A WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.

60 installs/wk local only

Codex MCP Tool

by x51xxx

MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review

95 installs/wk local only

Kimi MCP Server

by x51xxx

MCP server bridging AI assistants to Moonshot AI Kimi Code CLI for code analysis and review

322 installs/wk local only

Coding Agent Audit — questions

Answers built from our own checks of this server.

Why is there no uptime for Coding Agent Audit?

Coding Agent Audit runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package coding-agent-audit was installed 2 656 times last week.

How do I connect Coding Agent 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 runs locally, so the command pulls coding-agent-audit straight from pypi; nothing to host, nothing to sign up for.

How many people use Coding Agent Audit?

The pypi package coding-agent-audit was installed 2 656 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Coding Agent Audit open source?

We cannot say either way: written in Python and 0 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.