MCP Security Tools Server
An MCP server that integrates multiple security and reconnaissance tools (Nmap, Cariddi, ParamSpider, Metasploit, web scraping) for AI systems, enabling automated network scanning, API discovery, vulnerability testing, and remote access via ngrok.
README
MCP Security Tools Server
A comprehensive Model Context Protocol (MCP) server integrating multiple security and reconnaissance tools for AI systems (Claude, Grok, etc.).
📋 Table of Contents
- Overview
- Features
- Supported Tools
- Requirements
- Installation
- Quick Start
- Configuration
- Usage
- API Integration
- Troubleshooting
🎯 Overview
This MCP Server provides AI systems with access to enterprise-grade security testing tools. It enables:
- Automated Reconnaissance: Network scanning, API discovery, parameter enumeration
- API Security Testing: Endpoint discovery, parameter testing, vulnerability detection
- Web Application Security: JavaScript rendering, dynamic content extraction
- Exploitation & Testing: Metasploit framework integration for advanced testing
- Remote Access: Ngrok tunnel support for cloud-based AI systems
✨ Features
✅ Automated Setup - One-command installation with dependency checking
✅ Virtual Environment - Isolated Python environment for security
✅ Multiple Tools - 6 specialized security tools integrated
✅ API Key Management - Secure handling of authentication tokens
✅ Ngrok Integration - Remote access via secure tunnels
✅ AI-Ready - MCP protocol support for Claude, Grok, and other AI systems
✅ Comprehensive Logging - Detailed operation logs for debugging
✅ Error Handling - Graceful error management and recovery
✅ Skill Documentation - AI-friendly documentation (SKILL.md)
✅ Cross-Platform - Linux, macOS, and Windows support
🛠️ Supported Tools
1. Nmap - Network Reconnaissance
- Port scanning
- Service detection
- OS fingerprinting
- Network mapping
2. Cariddi - API Endpoint Discovery
- Sensitive endpoint detection
- Secret pattern matching
- API documentation analysis
- Vulnerability scanning
3. ParamSpider - Parameter Discovery
- Historical parameter extraction
- Hidden parameter discovery
- Injection point identification
- Endpoint parameter mapping
4. Metasploit Framework - Exploitation
- Vulnerability exploitation
- Payload generation
- Post-exploitation activities
- Social engineering
5. Web Scraper (ScrapingAnt) - Content Extraction
- JavaScript rendering
- Dynamic content extraction
- Proxy rotation
- Anti-detection features
6. MSFConsole - Advanced Penetration Testing
- Interactive exploitation
- Custom module development
- Automation scripting
- Multi-stage exploitation
📦 Requirements
System Requirements
- OS: Linux (Ubuntu 20.04+), macOS 10.14+, or Windows 10+
- Python: 3.8 or higher
- Memory: 2GB minimum (4GB recommended)
- Disk Space: 2GB for tools and dependencies
- Internet: Required for downloading tools and API access
Required Tools (System Level)
- Git - Version control
- Nmap - Network scanning
- Python 3.8+ - Programming language
Optional Tools
- Metasploit Framework - Advanced exploitation
- Docker - Containerized deployment
🚀 Installation
Option 1: Automated Setup (Recommended)
Linux/macOS:
# Clone repository
git clone https://github.com/antonlarimaraton/mcp-accses.git
cd mcp-accses
# Make setup script executable
chmod +x setup.sh
# Run setup
./setup.sh
Windows (PowerShell):
# Clone repository
git clone https://github.com/antonlarimaraton/mcp-accses.git
cd mcp-accses
# Run Python setup
python3 setup.py
Option 2: Manual Setup
# Create virtual environment
python3 -m venv venv
# Activate virtual environment
# Linux/macOS:
source venv/bin/activate
# Windows:
venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Install system tools
# Ubuntu/Debian:
sudo apt-get install nmap metasploit-framework
# macOS:
brew install nmap
brew install metasploit
⚡ Quick Start
1. Initial Setup
# Run setup script
./setup.sh
# Or with Python
python3 setup.py
2. Configure API Keys
# Copy example environment file
cp .env.example .env
# Edit with your API keys
nano .env
Required API keys:
- ScrapingAnt: https://www.scrapingant.com/
- Ngrok: https://dashboard.ngrok.com/
3. Start MCP Server
# Activate virtual environment
source venv/bin/activate
# Run server
python3 mcp_server.py
# Check server status
curl http://localhost:8000/status
4. Enable Ngrok Tunnel (Optional)
# Start with remote access
python3 mcp_server.py --ngrok
# Get public URL from ngrok
# Share with AI systems for remote access
⚙️ Configuration
Environment Variables (.env)
# API Keys
SCRAPINGANT_API_KEY=your_key_here
NGROK_AUTHTOKEN=your_token_here
# Server Settings
MCP_SERVER_PORT=8000
MCP_SERVER_HOST=0.0.0.0
DEBUG_MODE=false
# Tool Configuration
ENABLE_NMAP=true
ENABLE_CARIDDI=true
ENABLE_PARAMSPIDER=true
ENABLE_METASPLOIT=true
ENABLE_WEB_SCRAPER=true
MCP Configuration (mcp_config.json)
{
"name": "Security Tools MCP Server",
"version": "1.0.0",
"tools": {
"nmap": {"enabled": true},
"cariddi": {"enabled": true},
"paramspider": {"enabled": true},
"metasploit": {"enabled": true},
"web_scraper": {"enabled": true}
}
}
Ngrok Configuration (ngrok_config.json)
{
"authtoken": "your_ngrok_token",
"region": "ap",
"log_level": "info"
}
📖 Usage
Using with Claude (via MCP)
# Example: Scan for vulnerabilities
curl -X POST http://localhost:8000/tools/nmap \
-H "Content-Type: application/json" \
-d '{"target": "192.168.1.1", "args": "-sV"}'
Using with Grok or Other AI Systems
// JavaScript example
const response = await fetch('http://localhost:8000/tools/cariddi', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer your_api_key'
},
body: JSON.stringify({
url: 'https://target.com'
})
});
Direct Tool Usage
# Activate environment
source venv/bin/activate
# Nmap
nmap -sV target.com
# Cariddi
cariddi -u https://target.com
# ParamSpider
python3 tools/paramspider/paramspider.py -d target.com
# Web Scraper
python3 -c "from mcp_server import MCPServer; \
server = MCPServer(); \
result = server.scrape_with_api('https://target.com')"
🌐 API Integration
Endpoints
GET /status
GET /health
POST /tools/nmap
POST /tools/cariddi
POST /tools/paramspider
POST /tools/metasploit
POST /tools/scrape
GET /config
Response Format
{
"status": "success",
"tool": "nmap",
"timestamp": "2026-01-01T12:00:00Z",
"data": {
"results": [...],
"count": 42
},
"error": null
}
🔒 Security Considerations
⚠️ Important Security Notes:
- Authorization Only - Use only on targets you own or have written permission to test
- Legal Compliance - Ensure compliance with local laws and regulations
- API Keys - Never commit API keys to version control
- Rate Limiting - Implement rate limiting to avoid service disruption
- Logging - Enable comprehensive logging for audit trails
- Network - Use VPN for remote operations
- Credentials - Rotate API keys regularly
Best Practices
# Use .env for sensitive data
export $(cat .env | xargs)
# Enable debug logging
export DEBUG_MODE=true
# Run in isolated environment
source venv/bin/activate
# Monitor tool execution
tail -f setup.log
📊 Monitoring
Check Server Status
# Health check
curl http://localhost:8000/health
# Tool status
curl http://localhost:8000/status
# View logs
tail -f setup.log
Performance Metrics
# Monitor resource usage
watch -n 1 'ps aux | grep mcp_server'
# Check port usage
netstat -tulpn | grep 8000
🐛 Troubleshooting
Common Issues
1. "nmap not found"
# Ubuntu/Debian
sudo apt-get install nmap
# macOS
brew install nmap
# Windows
# Download from https://nmap.org/download.html
2. "API key invalid"
# Check .env file
cat .env | grep API_KEY
# Update with correct key
nano .env
3. "Permission denied"
# Run with appropriate permissions
sudo python3 mcp_server.py
# Or fix file permissions
chmod +x mcp_server.py
4. "Module not found"
# Activate virtual environment
source venv/bin/activate
# Reinstall dependencies
pip install -r requirements.txt
5. "Port already in use"
# Change server port
export MCP_SERVER_PORT=8001
# Or kill process on port 8000
lsof -ti:8000 | xargs kill -9
Debug Mode
# Enable debug logging
export MCP_DEBUG=1
export DEBUG_MODE=true
export LOG_LEVEL=DEBUG
# Run server with debug
python3 mcp_server.py --debug
# View detailed logs
tail -n 100 setup.log | grep ERROR
Log Files
# Check setup log
cat setup.log
# Watch real-time logs
tail -f setup.log
# Search for errors
grep ERROR setup.log
# Count occurrences
grep -c ERROR setup.log
📚 Additional Resources
Documentation
- SKILL.md - AI integration guide
- Requirements.txt - Dependencies list
- .env.example - Configuration template
Tool Documentation
External Links
- GitHub: https://github.com/antonlarimaraton/mcp-accses
- Issues: https://github.com/antonlarimaraton/mcp-accses/issues
🤝 Contributing
Contributions welcome! Please:
- Fork repository
- Create feature branch
- Commit changes
- Push to branch
- Create Pull Request
📝 License
MIT License - See LICENSE file for details
⚖️ Legal Notice
This tool is provided for authorized security testing only. Unauthorized access to computer systems is illegal. Users are responsible for compliance with all applicable laws and regulations.
🆘 Support
For issues and questions:
- Check Troubleshooting section
- Review Documentation
- Check GitHub Issues
- Contact maintainers
📋 Checklist for First-Time Use
- [ ] Clone repository
- [ ] Run setup script
- [ ] Configure API keys (.env)
- [ ] Install system tools
- [ ] Test individual tools
- [ ] Start MCP server
- [ ] Verify connectivity
- [ ] Setup Ngrok (optional)
- [ ] Test with AI system
- [ ] Review logs
🗺️ Project Status
| Component | Status | Notes |
|---|---|---|
| Setup Script | ✅ Ready | Automated installation |
| Nmap Integration | ✅ Ready | Full support |
| Cariddi Integration | ✅ Ready | API discovery |
| ParamSpider Integration | ✅ Ready | Parameter enumeration |
| Metasploit Integration | ✅ Ready | Exploitation framework |
| Web Scraper | ✅ Ready | JavaScript rendering |
| Ngrok Support | ✅ Ready | Remote access |
| MCP Protocol | ✅ Ready | AI integration |
| Documentation | ✅ Complete | SKILL.md included |
Last Updated: 2026-01-01
Version: 1.0.0
Maintainer: Security Tools Team
Ready to start? Run ./setup.sh or python3 setup.py now! 🚀
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。