Chris443C/MCP-Server-Claude-Gemini-OpenAI

Secure MCP Server - Claude, Gemini, ChatGPT

A secure Model Control Platform (MCP) server that provides controlled access to Claude, Gemini, and ChatGPT APIs with comprehensive data loss prevention (DLP) and file upload blocking capabilities.

🛡️ Security Features

• File Upload Blocking: Prevents any file uploads to external services
• DLP Scanning: Real-time content analysis for sensitive data
• Network Isolation: Controlled egress with firewall rules
• Authentication: JWT-based user authentication
• Audit Logging: Comprehensive request/response logging
• Rate Limiting: Prevents abuse and resource exhaustion

🏗️ Architecture

[Web Interface] → [FastAPI Gateway] → [DLP Scanner] → [AI Model APIs]
                      ↓
                [Audit Logger]
                      ↓
                [Redis Cache]

🚀 Quick Start

Prerequisites

• Python 3.9+
• Node.js 18+ (for frontend)
• Redis (for caching and sessions)
• ClamAV (for malware scanning)

Installation

1. Clone and setup backend:

git clone <repository>
cd MCP-Server-Claude-Gemini-OpenAI
pip install -r requirements.txt

2. Setup frontend:

cd frontend
npm install
npm run build

3. Configure environment:

cp .env.example .env
# Edit .env with your API keys and settings

4. Run the server:

python main.py

🔧 Configuration

Environment Variables

Create a .env file with:

# API Keys
OPENAI_API_KEY=your_openai_key
ANTHROPIC_API_KEY=your_anthropic_key
GOOGLE_API_KEY=your_google_key

# Security
SECRET_KEY=your_secret_key
JWT_ALGORITHM=HS256
ACCESS_TOKEN_EXPIRE_MINUTES=30

# Redis
REDIS_URL=redis://localhost:6379

# DLP Settings
MAX_CONTENT_LENGTH=1048576
BLOCKED_DOMAINS=dropbox.com,drive.google.com,onedrive.live.com

# Monitoring
PROMETHEUS_PORT=9090
LOG_LEVEL=INFO

🎯 Usage

1. Access the web interface: http://localhost:8000
2. Authenticate with your credentials
3. Select a model (Claude, Gemini, or ChatGPT)
4. Enter your prompt (file uploads are automatically blocked)
5. View responses with full audit trail

🔒 Security Measures

File Upload Prevention

• Content-type validation
• File signature detection
• Size limits enforcement
• Malware scanning with ClamAV

Network Controls

• Egress firewall rules
• Proxy-based DLP
• Domain blocking
• Rate limiting

Data Protection

• Input sanitization
• Output filtering
• Audit logging
• Session management

📊 Monitoring

• Prometheus metrics at /metrics
• Health checks at /health
• Audit logs in structured format
• Real-time alerts for security events

🚨 Security Alerts

The system monitors for:

• File upload attempts
• Large data transfers
• Unusual API usage patterns
• Authentication failures
• DLP violations

📝 API Documentation

Once running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

MIT License - see LICENSE file for details

🆘 Support

For security issues, please contact the security team directly. For general support, create an issue in the repository.