mcp-security-hub - A growing collection of MCP servers bringing offen

项目说明

Offensi MCP Servers

![Build Status]()
![Security Scan]()
![License: MIT]()
![MCP Protocol]()

Production-ready, Dockerized MCP (Model Context Protocol) servers for offensi tools. Enable AI assistants like Claude to perform security assessments, scanning, and binary analysis.

<p align="center">
<img src=" alt="38 MCPs"/>
<img src=" alt="300+ Tools"/>
<img src=" alt="Docker Ready"/>
</p>

Features

Quick Start

Configure Claude Desktop / Claude Code

Important: You must build the images first with docker-compose build before using them.

Copy the example config to your Claude Desktop configuration:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

For project-le, copy .mcp.json to your project root. See examples/ for full configuration templates with all MCPs and mount patterns.

A MCP Servers

Reconnaissance (8 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| nmap-mcp | 8 | Port scanning, service detection, OS fingerprinting, NSE scripts |
| shodan-mcp | - | Wrapper for official Shodan MCP |
| pd-tools-mcp | - | Wrapper for ProjectDiscovery tools (subfinder, httpx, katana) |
| whatweb-mcp | 5 | Web technology fingerprinting and CMS detection |
| masscan-mcp | 6 | High-speed port scanning for large networks |
| zoomeye-mcp | - | Wrapper for ZoomEye MCP - Cyberspace search engine |
| networksdb-mcp | 4 | IP/ASN/DNS lookups via NetworksDB |
| externalattacker-mcp | 6 | Attack surface mapping with ExternalAttacker |

Web Security (6 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| nuclei-mcp | 7 | Template-based scanning with 8000+ templates |
| sqlmap-mcp | 8 | SQL injection detection and exploitation |
| nikto-mcp | - | Wrapper for Nikto MCP web ser |
| ffuf-mcp | 9 | Web fuzzing for directories, files, parameters, and hosts |
| waybackurls-mcp | 3 | Fetch historical URLs from Wayback Machine for reconnaissance |
| burp-mcp | - | Wrapper for official Burp Suite MCP |

Binary Analysis (6 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| radare2-mcp | 32 | Wrapper for official radare2-mcp - disassembly, decompilation |
| binwalk-mcp | 6 | Firmware analysis, signature scanning, extraction |
| yara-mcp | 7 | Pattern matching for malware classification |
| capa-mcp | 5 | Capability detection in executables |
| ghidra-mcp | - | Wrapper for pyghidra-mcp - Headless AI-powered reverse engineering |
| ida-mcp | - | Wrapper for ida-pro-mcp - IDA Pro integration |

Blockchain Security (3 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| daml- | 1 | DAML access-control table generation and run tracking |
| medusa-mcp | 4 | High-performance smart contract fuzzer for Solidity |
| solazy-mcp | 8 | Solana sBPF static analysis and reverse engineering |

Cloud Security (3 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| tri | 7 | Container, filesystem, and IaC scanning |
| prowler-mcp | 6 | AWS/Azure/GCP security auditing and compliance |
| roadrecon-mcp | 6 | Azure AD enumeration via RoadRecon |

Secrets Detection (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| gitleaks-mcp | 5 | Find secrets and credentials in git repos and files |

Exploitation (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| searchsploit-mcp | 5 | Exploit-DB search and retrieval |

Fuzzing (2 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| boofuzz-mcp | 4 | Network protocol fuzzing using Boofuzz |
| dharma-mcp | 2 | Grammar-based test case generation |

OSINT (2 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| maigret-mcp | - | Wrapper for mcp-maigret - Username OSINT across 2500+ sites |
| dnstwist-mcp | - | Wrapper for mcp-dnstwist - Typosquatting/phishing detection |

Threat Intelligence (2 servers)

| Server | Tools | Description |
|--------|-------|-------------|
| | - | Wrapper for mcp- - Malware analysis and threat intel |
| otx-mcp | - | Wrapper for OTX MCP - AlienVault Open Threat Exchange |

Acti (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| bloodhound-mcp | 75+ | Wrapper for BloodHound-MCP-AI - AD attack path analysis |

Password Cracking (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| hashcat-mcp | - | Wrapper for hashcat-mcp - Natural language hash cracking |

Code Security (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| semgrep-mcp | 7 | Wrapper for Semgrep MCP - Static code analysis with 5000+ rules |

Meta (1 server)

| Server | Tools | Description |
|--------|-------|-------------|
| mcp-scan | - | Wrapper for mcp-scan - Scan MCP servers for |

Usage Examples

Network Reconnaissance

Assessment

Binary Analysis

Security Hardening

All containers implement defense-in-depth:

| Control | Implementation |
|---------|----------------|
| Non-root execution | Runs as mcpuser (UID 1000) |
| Minimal images | Alpine/Debian slim base images |
| Dropped capabilities | cap_drop: ALL, selective cap_add |
| No pri escalation | security_opt: no-new-pri:true |
| Read-only mounts | Sample directories mounted read-only |
| Resource limits | CPU and memory constraints |
| Health checks | Built-in container health monitoring |
| scanning | Tri in CI/CD pipeline |

Project Structure

Testing

Legal & Compliance

These tools are for authorized security testing only.

Before using:

1. Obtain written authorization from the target owner
2. Define scope - targets, timeline, allowed acti
3. Maintain audit logs of all operations
4. Follow responsible disclosure for any findings

Unauthorized access to computer systems is illegal. Users are responsible for compliance with applicable laws.

Contributing

Contributions welcome! To add a new MCP server:

1. Use Dockerfile.template as your starting point
2. Follow security hardening practices (non-root, minimal image)
3. Include health checks and comprehensi
4. Ensure Trivy scan passes (no HIGH/CRITICAL )
5. Add tests to tests/test_mcp_servers.py

Acknowledgments

License

MIT License - See LICENSE

---

<p align="center">
<strong>Maintained by <a href="
<br>
_{Making AI-powered security testing accessible}
</p>

项目信息

开发语言：Python

Star 数：797

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。