PostgreSQL MCP Server

中文 | English

A Model Context Protocol (MCP) server that provides tools for interacting with a PostgreSQL database. It enables AI assistants to execute SQL queries, explain statements, create tables, and list database tables via the MCP protocol.

✨ Features

• Interact with Databases via AI: Enables LLMs to perform database operations through a structured protocol.
• Secure Toolset: Separates read and write operations into distinct, authorizable tools (read_query, write_query).
• Schema Management: Allows for table creation (create_table) and listing (list_tables).
• Query Analysis: Provides a tool to analyze query execution plans (explain_query).
• Multiple Transport Modes: Supports stdio, Server-Sent Events (sse), and streamableHttp for flexible client integration.
• Environment-Based Configuration: Easily configurable using a .env file.

🛠️ Available Tools

The server exposes the following tools for MCP clients to invoke:

🔌 Server Modes

You can select the transport protocol by setting the SERVER_MODE environment variable.

stdio

The server communicates over standard input and output. This is the default mode and is ideal for local testing or direct integration with command-line-based MCP clients.

sse

The server communicates using Server-Sent Events (SSE). When this mode is enabled, the server will start an HTTP service and listen for connections.

• SSE Endpoint: http://localhost:8088/sse
• Message Endpoint: http://localhost:8088/message

streamableHttp

The server uses the Streamable HTTP transport, a more modern and flexible HTTP-based transport for MCP.

• Endpoint: http://localhost:8088/mcp

🤝 Contributing

Contributions are welcome! If you find any bugs, have feature requests, or suggestions for improvement, please feel free to submit a Pull Request or open an Issue.

1. Fork the Project.
2. 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.

📄 License

This project is open source and is licensed under the MIT License.

🚀 Quick Start

Prerequisites

• Go 1.23 or later
• A PostgreSQL database server

Installation

1. Clone the repository:

   Copy

   git clone https://github.com/leixiaotian1/pgsql-mcp-server.git
   cd pgsql-mcp-server

2. Install dependencies:

   Copy

   go mod download

3. Build the MCP server:

   Copy

   go build -o pgsql-mcp-server

Configuration

The pg-mcp-server requires database connection details to be provided via environment variables. Create a .env file in the project root with the following variables:

DB_HOST=localhost      # PostgreSQL server host
DB_PORT=5432           # PostgreSQL server port
DB_NAME=postgres       # Database name
DB_USER=your_username  # Database user
DB_PASSWORD=your_pass  # Database password
DB_SSLMODE=disable     # SSL mode (disable, require, verify-ca, verify-full)
SERVER_MODE=stdio      # Server mode (stdio, sse, streamableHttp)

Usage

Running the Server

./pgsql-mcp-server

MCP Configuration

To use this server with an MCP-enabled AI assistant, add the following to your MCP configuration:

{
  "mcpServers": {
    "pgsql-mcp-server": {
      "command": "/path/to/pgsql-mcp-server",
      "args": [],
      "env": {
        "DB_HOST": "localhost",
        "DB_PORT": "5432",
        "DB_NAME": "postgres",
        "DB_USER": "your_username",
        "DB_PASSWORD": "your_password",
        "DB_SSLMODE": "disable",
        "SERVER_MODE": "stdio"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

DOCKER DEPLOYMENT