# MCP implementation security review

> MCP implementation security review is an open-source agent skill for security. Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — auth. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/github/awesome-copilot/tree/main/skills/mcp-implementation-security-review
- **Repository:** https://github.com/github/awesome-copilot
- **GitHub stars:** 41,254
- **License:** MIT
- **Skill name:** mcp-implementation-security-review
- **Collection:** https://github.com/github/awesome-copilot
- **Categories:** security
- **Listing updated:** 2026-11-17

## About

Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema validation, official-SDK usage, RCE vectors, and the OWASP MCP Top 10 — producing a report with file/line evidence. Use this skill when:
- Reviewing an MCP server implementation for security before release
- Checking a server against the baseline controls (MCP-01 to MCP-05) and the OWASP MCP Top 10
- Auditing tools for RCE vectors (command/code injection, unsafe deserialization, path traversal, SSTI, dependency hijacking, SSRF)
- Verifying auth, session, rate-limiting, and input-validation controls on a network-exposed server
- Reviewing MCP client code that handles untrusted server responses and session IDs
- Requests like "review this MCP server for security" or "is my MCP server implementation secure?"

## When your agent uses it

> Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema validation, official-SDK usage, RCE vectors, and the OWASP MCP Top 10 — producing a report with file/line evidence. Use this skill when: - Reviewing an MCP server implementation for security before release - Checking a server against the baseline controls (MCP-01 to MCP-05) and the OWASP MCP Top 10 - Auditing tools for RCE vectors (command/code injection, unsafe deserialization, path traversal, SSTI, dependency hijacking, SSRF) - Verifying auth, session, rate-limiting, and input-validation controls on a network-exposed server - Reviewing MCP client code that handles untrusted server responses and session IDs - Requests like "review this MCP server for security" or "is my MCP server implementation secure?"

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/github/awesome-copilot/tree/HEAD/skills/mcp-implementation-security-review)
- [License: MIT](https://github.com/github/awesome-copilot/tree/HEAD/skills/mcp-implementation-security-review)

## Install

### Claude Code

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

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

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

### Codex

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

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

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

### Cursor

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

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

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

### Gemini CLI

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

```sh
gemini skills install https://github.com/github/awesome-copilot.git --path skills/mcp-implementation-security-review
```

Or copy the folder to `~/.gemini/skills/mcp-implementation-security-review` yourself.

### VS Code

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

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

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

### Other agents

Get the folder:

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

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

## FAQ

### How do I install MCP implementation security review in Claude Code?

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

### Does MCP implementation security review 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 implementation security review?

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 implementation security review?

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

## Alternatives

- [Security review](https://ai-powered.com/skills/security-review): Security review is an open-source agent skill for security.
- [Tm7 threat model](https://ai-powered.com/skills/tm7-threat-model): Tm7 threat model is an open-source agent skill for security.
- [Audit integrity](https://ai-powered.com/skills/audit-integrity): Audit integrity is an open-source agent skill for security.
- [Threat model analyst](https://ai-powered.com/skills/threat-model-analyst): Threat model analyst is an open-source agent skill for security.
- [Spring security](https://ai-powered.com/skills/spring-security): Spring security is an open-source agent skill for security.
- [Github actions hardening](https://ai-powered.com/skills/github-actions-hardening): Github actions hardening is an open-source agent skill for developer tools.
- [Secret scanning](https://ai-powered.com/skills/secret-scanning): Secret scanning is an open-source agent skill for security.
- [Dependabot](https://ai-powered.com/skills/dependabot): Dependabot is an open-source agent skill for security.

---
Source: https://ai-powered.com/skills/mcp-implementation-security-review
