Skip to content
Skill

MCP security audit

Audit MCP (Model Context Protocol) server configurations for security issues

Install
Scripts
None
Platforms
Claude Code, Codex, Cursor
GitHub stars
41.3K
Last commit
1 day ago
License
MIT
Listing updated
today

When your agent uses it

Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP server args for hardcoded secrets or shell injection patterns - Validating that MCP package-runner dependencies use exact reviewed versions, not bare names, @latest, or ranges - Detecting mutable npm/npx, bunx, pnpm dlx, yarn dlx, npm exec, uvx, uv tool run, and pipx run references in MCP configurations - Auditing which MCP servers a project registers and whether they're on an approved list - Checking for environment variable usage vs. hardcoded credentials in MCP configs - Any request like "is my MCP config secure?", "audit my MCP servers", or "check .mcp.json" keywords: [mcp, security, audit, secrets, shell-injection, supply-chain, governance]

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 1 file (14 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

Copy the skill folder to ~/.claude/skills/mcp-security-audit to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/mcp-security-audit &&
cp -R "$tmp/skills/mcp-security-audit" ~/.claude/skills/mcp-security-audit &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/mcp-security-audit inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/mcp-security-audit to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/mcp-security-audit &&
cp -R "$tmp/skills/mcp-security-audit" ~/.agents/skills/mcp-security-audit &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/mcp-security-audit inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/mcp-security-audit to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/mcp-security-audit &&
cp -R "$tmp/skills/mcp-security-audit" ~/.cursor/skills/mcp-security-audit &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/mcp-security-audit inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/github/awesome-copilot.git --path skills/mcp-security-audit

Or copy the folder to ~/.gemini/skills/mcp-security-audit yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/mcp-security-audit:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/github/awesome-copilot.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/mcp-security-audit &&
cp -R "$tmp/skills/mcp-security-audit" ~/.copilot/skills/mcp-security-audit &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/mcp-security-audit inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/github/awesome-copilot.git

Then copy awesome-copilot/skills/mcp-security-audit into your agent's skills folder as mcp-security-audit. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

MCP security audit FAQ

How do I install MCP security audit in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/mcp-security-audit to use it in all your projects, or to .claude/skills/mcp-security-audit in one project.

Does MCP security audit run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use MCP security audit?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

What are the best alternatives to MCP security audit?

The closest alternatives to MCP security audit are Tm7 threat model, Spring security, Audit integrity, Security review and MCP implementation security review.

More from github/awesome-copilot

  1. Design or review infrastructure, deployment, CI/CD, Docker, Kubernetes, health checks, rollback, feature flags, production readiness, and mo

    • Open source
    • 41.3K GitHub stars
    • Cloud and infrastructure
  2. Stop coding agents from shipping generic UI

    • Open source
    • 41.3K GitHub stars
  3. Cross-references C# Web API controllers/DTOs against their TypeScript/JavaScript consumers (React, Angular, Vue, Svelte, Node.js, or hand-wr

    • Open source
    • 41.3K GitHub stars
  4. Serves as a reviewer of the codebase with instructions on looking for Apple App Store optimizations or rejection reasons.

    • Open source
    • 41.3K GitHub stars
  5. Triage and resolve Arch Linux issues with pacman, systemd, and rolling-release best practices.

    • Open source
    • 41.3K GitHub stars

Alternatives to MCP security audit

  1. Creates valid Microsoft Threat Modeling Tool (.tm7) files compatible with the Microsoft Threat Modeling Tool v7.3+

    • Open source
    • 41.3K GitHub stars
    • Security
  2. Configure, test and review Spring Security 6/7 in Spring Boot 3/4 apps: SecurityFilterChain lambda DSL, method security, OAuth2 resource ser

    • Open source
    • 41.3K GitHub stars
    • Security
  3. Enforce output quality, evidence verification, and quality gates across security audits

    • Open source
    • 41.3K GitHub stars
    • Security
  4. AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component intera

    • Open source
    • 41.3K GitHub stars
    • Security
  5. Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — auth

    • Open source
    • 41.3K GitHub stars
    • Security
  6. Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml)

    • Open source
    • 41.3K GitHub stars
    • Developer tools