# mcp-security-hub

This skill spins up 38 Dockerized MCP servers for offensive security tooling and wires them into an AI assistant.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 987 installs · ★ 12
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/security-skills/tree/HEAD/skills/mcp-security-hub/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/mcp-security-hub

## What it does

The skill deploys and orchestrates 38 MCP servers covering more than 300 security tools. The set spans reconnaissance (Nmap, Shodan, Masscan, WhatWeb, ZoomEye, ProjectDiscovery), web security (Nuclei, SQLMap, Nikto, ffuf, Burp Suite), binary analysis (radare2, Ghidra, Binwalk, YARA, Capa, IDA Pro), blockchain, cloud (Trivy, Prowler, RoadRecon), secrets detection, fuzzing, OSINT, Active Directory and password cracking. Scans, binary triage and pentest tasks start from a plain sentence in chat.

Setup runs through Docker: clone the repository, then `docker-compose build` — you can build only what you need, for instance `nmap-mcp nuclei-mcp gitleaks-mcp`. Servers are then declared in the client config, either `claude_desktop_config.json` or a `.mcp.json` at the project root. Several servers need volume mounts: gitleaks reads repos from `/app/target`, radare2 reads binaries from `/samples`, trivy needs `docker.sock`. Skip the mounts and those tools see nothing.

Docker 20.10+ and Docker Compose 2.0+ are required. External services need keys — `SHODAN_API_KEY`, `VT_API_KEY`, `ZOOMEYE_API_KEY`, `BURP_API_KEY` — passed into the container with `-e`. Nmap scanning needs the `--cap-add=NET_RAW` flag.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

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

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/security-skills --skill mcp-security-hub -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/mcp-security-hub/SKILL.md

## When to use it
- stand up MCP servers for security tools with one build command
- scan a subnet for open ports and fingerprint the OS
- check a site for critical vulnerabilities with Nuclei templates
- hunt leaked keys and credentials across a git repository
- pull strings and imports out of a suspicious binary

## Example prompts
- Bring up nmap-mcp and scan 192.168.1.0/24 for open ports
- Check https://example.com for critical vulnerabilities with nuclei
- Find secrets in the repository at /app/target/myrepo

## Similar
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 57000 installs
- [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · 45400 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 54800 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 70200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [reason-machines/security-skills](https://affpapa.org/en/nevibecode/by/reason-machines/security-skills.md) — 24 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