# pentester-mcp-security-tools

pentester-mcp-security-tools connects over 200 penetration testing tools to AI coding agents via MCP. Useful for automated port scanning and directory fuzzing from chat.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 261 installs · ★ 13 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/pentester-mcp-security-tools/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/pentester-mcp-security-tools

## What it does

The skill connects your AI assistant to an MCP server bundling security tools such as `nmap`, `sqlmap`, `ffuf`, `nuclei`, and `impacket`. Each utility runs via isolated Python subprocess calls without a raw shell. This prevents command injection vulnerabilities. Every tool enforces execution timeouts and truncates console outputs to 8000 characters to keep context windows clean.

You can run the environment inside a Docker container or directly on Kali Linux via a Python virtual environment. Selecting which scanners stay active happens in `configs/example-config.yaml`. Without an active Docker daemon or pre-installed security packages on the host, the server will fail to start.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentester-mcp-security-tools -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/pentester-mcp-security-tools/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/pentester-mcp-security-tools/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentester-mcp-security-tools -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/pentester-mcp-security-tools/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentester-mcp-security-tools -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/pentester-mcp-security-tools/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/security-skills skills/pentester-mcp-security-tools
```

2. **Manually: put the files in place**
- File: `.github/skills/pentester-mcp-security-tools/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentester-mcp-security-tools -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/security-skills --path skills/pentester-mcp-security-tools
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/pentester-mcp-security-tools/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill pentester-mcp-security-tools -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/security-skills/tree/HEAD/skills/pentester-mcp-security-tools/SKILL.md

## When to use it
- run port and service discovery using `nmap`
- discover hidden web routes and endpoints with `ffuf`
- audit web request parameters for SQL injection via `sqlmap`
- dump Active Directory domain credentials through `impacket`

## Example prompts
- Scan 192.168.1.1 with nmap using default scripts
- Test target.com/index.php?id=5 for SQL injection using sqlmap
- Fuzz directories on test.local using ffuf and my wordlist

## Similar
- [shannon-ai-pentester](https://affpapa.org/en/nevibecode/skills/shannon-ai-pentester.md) — skill · 1700 installs
- [cairn-ai-pentest](https://affpapa.org/en/nevibecode/skills/cairn-ai-pentest.md) — skill · 378 installs
- [penetration-testing](https://affpapa.org/en/nevibecode/skills/devops-skills-penetration-testing.md) — skill · 414 installs
- [shannon](https://affpapa.org/en/nevibecode/skills/shannon.md) — skill · 3000 installs
- [container-escape-techniques](https://affpapa.org/en/nevibecode/skills/container-escape-techniques.md) — skill · 3900 installs
- [docker-security-guide](https://affpapa.org/en/nevibecode/skills/docker-security-guide.md) — skill · 626 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 129 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
