🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI
The security audit CLI for Model Context Protocol (MCP) servers
Scan your AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection, and supply-chain risks — before the model runs something you regret.
Install · Quickstart · Rules · CI Integration · Roadmap
The Model Context Protocol (MCP) is the open standard that lets AI assistants — Claude Desktop, Cursor, VS Code Copilot, Windsurf, Cline, Zed — call external tools, read your files, and execute commands. Adoption exploded to thousands of public MCP servers, and security research keeps confirming the same story: the MCP attack surface is real and largely unguarded.
A single line in your claudedesktopconfig.json or .cursor/mcp.json can hand an AI model:
- 🔑 Your credentials — API keys and tokens hardcoded in plaintext env blocks - 📦 Unpinned packages — npx -y some-mcp-server fetches whatever the latest release is, every launch (the classic rug pull) - 🐚 Arbitrary execution — curl … bash installers and bash -c wrappers - 🗂️ Your whole disk — filesystem servers rooted at / or ~ - 🕳️ Poisoned tool descriptions — hidden instructions injected straight into the model's context (tool poisoning) - 🌐 Unauthenticated remote servers — plaintext HTTP endpoints anyone can invoke
mcp-audit-tool finds all of these in seconds. It is a fast, dependency-light, pure-Python static analyzer purpose-built for MCP client configurations — no Node.js, no Docker, no LLM API keys required.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/graygnatconsole--mcp-audit-tool.html)
MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads
yagyeshVyas/VibeGuardFree security & privacy scanner for AI-coded apps. 699 rules, 76 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for l
HUA503/mcprismFast single-binary security scanner for MCP (Model Context Protocol) servers — config audit, live capability enumeration, tool-poisoning detection & risk grading. Zero deps, fully offline — trivy for
agent-chaperone/agent-chaperoneScreens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Shalimov04/mcp-airlockStateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing
CTRLRun/ctrlrunThe execution safety layer for AI agents.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.