FastAPI MCP Server
A production-ready Model Context Protocol server built with FastAPI, featuring JWT authentication, PostgreSQL database support, Redis caching, and comprehensive health monitoring for building secure async API applications.
README
MCP Server
एक production-ready Model Context Protocol (MCP) server जो FastAPI framework का उपयोग करके बनाई गई है।
विशेषताएं (Features)
- 🚀 FastAPI Framework: High-performance async API server
- 🔒 Security: JWT authentication और secure coding practices
- 🗄️ Database: PostgreSQL के साथ asyncpg
- 📦 Caching: Redis integration
- 🐳 Docker Ready: Production-ready containerization
- 📊 Health Checks: Built-in health monitoring
- 🔧 Development Ready: Comprehensive testing और development tools
आवश्यकताएं (Requirements)
- Python 3.11+
- PostgreSQL 13+
- Redis 6+
- Docker (optional)
इंस्टॉलेशन (Installation)
1. Repository Clone करें
git clone <repository-url>
cd mcp-server
2. Virtual Environment बनाएं
python -m venv venv
source venv/bin/activate # Linux/Mac
# या
venv\\Scripts\\activate # Windows
3. Dependencies Install करें
pip install -r requirements.txt
4. Environment Variables सेट करें
.env file बनाएं:
# Database
DATABASE_URL=postgresql://username:password@localhost:5432/mcp_db
# Redis
REDIS_URL=redis://localhost:6379/0
# Security
SECRET_KEY=your-secret-key-here
JWT_ALGORITHM=HS256
JWT_EXPIRE_MINUTES=30
# Server
HOST=0.0.0.0
PORT=8000
DEBUG=false
Usage
Development Mode
uvicorn main:app --reload --host 0.0.0.0 --port 8000
Production Mode
uvicorn main:app --host 0.0.0.0 --port 8000 --workers 4
Docker के साथ
# Build करें
docker build -t mcp-server .
# Run करें
docker run -p 8000:8000 --env-file .env mcp-server
API Documentation
Base URL
http://localhost:8000
Interactive Documentation
- Swagger UI: http://localhost:8000/docs
- ReDoc: http://localhost:8000/redoc
Main Endpoints
Health Check
GET /health
Server की health status check करता है।
API Endpoints
GET /api/v1/status
POST /api/v1/connect
GET /api/v1/tools
POST /api/v1/tools/{tool_name}/call
Development
Code Quality
# Format code
black .
# Sort imports
isort .
# Lint code
flake8 .
# Type checking
mypy .
Testing
# सभी tests run करें
pytest
# Coverage के साथ
pytest --cov=src tests/
# Specific test file
pytest tests/test_main.py
Project Structure
mcp-server/
├── src/ # Source code
│ ├── main.py # FastAPI application
│ ├── models/ # Pydantic models
│ ├── routes/ # API routes
│ ├── services/ # Business logic
│ ├── database/ # Database configuration
│ └── utils/ # Utility functions
├── tests/ # Test files
├── requirements.txt # Python dependencies
├── Dockerfile # Docker configuration
├── docker-compose.yml # Docker Compose (optional)
├── .env.example # Environment variables template
├── .gitignore # Git ignore patterns
├── .dockerignore # Docker ignore patterns
└── README.md # This file
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
DATABASE_URL |
PostgreSQL connection URL | Required |
REDIS_URL |
Redis connection URL | redis://localhost:6379/0 |
SECRET_KEY |
JWT secret key | Required |
JWT_ALGORITHM |
JWT algorithm | HS256 |
JWT_EXPIRE_MINUTES |
JWT expiration time | 30 |
HOST |
Server host | 0.0.0.0 |
PORT |
Server port | 8000 |
DEBUG |
Debug mode | false |
Database Setup
-- PostgreSQL database बनाएं
CREATE DATABASE mcp_db;
-- User बनाएं (optional)
CREATE USER mcp_user WITH PASSWORD 'secure_password';
GRANT ALL PRIVILEGES ON DATABASE mcp_db TO mcp_user;
Redis Setup
# Redis start करें
redis-server
# या Docker के साथ
docker run -d -p 6379:6379 redis:alpine
Security Features
- JWT-based authentication
- Password hashing with bcrypt
- CORS protection
- Rate limiting
- Input validation
- SQL injection protection
- XSS protection
Monitoring
Health Checks
# Server health check
curl http://localhost:8000/health
# Database connection check
curl http://localhost:8000/health/db
# Redis connection check
curl http://localhost:8000/health/redis
Logging
Logs /logs/ directory में store होते हैं। Production में proper logging configuration set करें।
Deployment
Docker Deployment
# Production image build करें
docker build -t mcp-server:latest .
# Docker Compose के साथ
docker-compose up -d
Manual Deployment
# Gunicorn के साथ
gunicorn main:app -w 4 -k uvicorn.workers.UvicornWorker
Contributing
- Fork करें
- Feature branch बनाएं (
git checkout -b feature/amazing-feature) - Commit करें (
git commit -m 'Add amazing feature') - Push करें (
git push origin feature/amazing-feature) - Pull Request open करें
License
यह project MIT license के under है।
Support
समस्याओं के लिए GitHub Issues create करें या documentation पढ़ें।
Changelog
v1.0.0
- Initial release
- FastAPI integration
- JWT authentication
- Redis caching
- Docker support
- Comprehensive documentation
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。