Pgsql MCP Server

🚀 PostgreSQL MCP Server

A powerful tool server based on the Model Context Protocol (MCP), supporting interactions with PostgreSQL databases through MCP calls.

🚀 Quick Start

This project is built on the FastMCP framework and utilizes the SQLAlchemy and asyncpg libraries to achieve efficient asynchronous database operations, ensuring high efficiency and responsiveness when handling database requests.

✨ Features

• Asynchronous and Efficient: Fully asynchronous implementation based on asyncio, using asyncpg as a high-performance asynchronous PostgreSQL driver.
• Transaction Security: DDL, DML, and DCL operations are all executed within transactions, equipped with error handling and rollback mechanisms.
• Easy Deployment: Start the server through a simple command-line interface.

📦 Installation

Make sure you have Python 3.8+ installed. It is recommended to use uvx for installation:

uvx pgsql-mcp-server --dsn postgresql://user:password@localhost:5432/db

💻 Usage Examples

Basic Usage

You can use the official MCP inspection tool to visually check the tools provided by the server, view their parameters and descriptions, and execute test calls.

npx @modelcontextprotocol/inspector uvx pgsql-mcp-server --dsn "postgresql://user:password@host:port/database"

This will start a local web service. Open the provided URL in your browser to start debugging.

🤝 Contribution

Contributions are welcome! If you have any suggestions for improvement, feature requests, or find any issues, please feel free to:

1. Open an issue for discussion.
2. Fork the repository and create your feature branch (git checkout -b feature/AmazingFeature).
3. Commit your changes (git commit -m 'Add some AmazingFeature').
4. Push to the branch (git push origin feature/AmazingFeature).
5. Open a Pull Request.