Mymcpserv

🚀 Modern Control Protocol (MCP) Server

A modern and scalable MCP server implementation that supports multiple AI providers, advanced monitoring, and powerful conversation management.

✨ Features

• Multi-provider AI support (OpenAI, Anthropic, Google AI, Azure)
• Real-time streaming responses
• Conversation management and history
• Function calling and tool usage
• Vector database integration
• Semantic caching
• Prometheus metrics and Grafana dashboards
• Rate limiting and error handling
• PostgreSQL data persistence
• Redis caching
• Elasticsearch search
• Docker containerization

🚀 Quick Start

1. Clone the repository.
2. Copy the environment variable template:

   cp .env.example .env
   

3. Update the environment variables in the .env file.
4. Start the service using Docker Compose:

   docker-compose up -d
   

📚 Documentation

After the server is running, access the following links:

• API documentation: http://localhost:8000/docs
• ReDoc documentation: http://localhost:8000/redoc

📊 Monitoring

• Prometheus metrics: http://localhost:9090
• Grafana dashboards: http://localhost:3000

🔧 Technical Details

Prerequisites

• Python 3.9+
• PostgreSQL database
• Redis cache
• Elasticsearch search
• Docker and Docker Compose

Local Development Setup

1. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # Linux/Mac
   # Or
   .\venv\Scripts\activate  # Windows
   

2. Install the dependencies:

   pip install -r requirements.txt
   

3. Start the development server:

   uvicorn app.main:app --reload
   

Testing

Run the test cases:

pytest

🏗️ System Architecture

The MCP server is designed with a microservices architecture:

• Build REST APIs using FastAPI.
• Use PostgreSQL for data persistence.
• Employ Redis for caching and rate limiting.
• Leverage Elasticsearch for search functionality.
• Implement vector storage with Qdrant.
• Manage monitoring with Prometheus and Grafana.

📄 API Endpoints

• /api/v1/mcp/prompts: Prompt management
• /api/v1/mcp/conversations: Conversation handling
• /api/v1/mcp/conversations/{id}/complete: AI completion requests
• /metrics: Prometheus metrics
• /health: Health check endpoint

📄 License

This project is licensed under the MIT License. Please refer to MIT License for the specific terms.