Postgresql Explorer

🚀 PostgreSQL MCP Server

A PostgreSQL MCP server implemented using the Model Context Protocol (MCP) Python SDK. MCP is an open protocol that enables LLM applications to seamlessly integrate with external data sources. This server allows AI agents to interact with PostgreSQL databases through a standardized interface.

🚀 Quick Start

To start using the PostgreSQL MCP Server, follow the steps in the "Installation" and "Usage Examples" sections below.

✨ Features

• List database schemas
• List tables within a schema
• Describe table structures
• List table constraints and relationships
• Retrieve foreign key information
• Execute SQL queries

📦 Installation

Automatic Installation via Smithery

Automatically install the PostgreSQL MCP Server for Claude Desktop through Smithery:

npx -y @smithery/cli install @gldc/mcp-postgres --client claude

Manual Installation

1. Clone this repository:

git clone <repository-url>
cd mcp-postgres

2. Create and activate a virtual environment (recommended):

python -m venv venv
source venv/bin/activate  # On Windows, use: venv\Scripts\activate

3. Install the dependencies:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

1. Start the MCP server by providing the PostgreSQL connection string:

python postgres_server.py "postgresql://username:password@host:port/database"

2. The server provides the following tools:

• query: Execute SQL queries
• list_schemas: List all available schemas
• list_tables: List all tables within a specific schema
• describe_table: Get detailed information about the table structure
• get_foreign_keys: Retrieve the foreign key relationships of a table
• find_relationships: Discover explicit and implicit relationships between tables

Advanced Usage

To integrate this server into an MCP-compatible tool (such as Cursor), add it to your ~/.cursor/mcp.json:

{
  "servers": {
    "postgres": {
      "command": "/path/to/venv/bin/python",
      "args": [
        "/path/to/postgres_server.py",
        "postgresql://username:password@host:5432/database?ssl=true"
      ]
    }
  }
}

Replace:

• /path/to/venv with the path to your virtual environment
• /path/to/postgres_server.py with the absolute path to the server script
• The connection string with your PostgreSQL database credentials

⚠️ Important Note

Ensure the security of the mcp.json file as it contains sensitive database credentials.

🔧 Technical Details

Security Tips

• Never expose sensitive database credentials in your code.
• Use environment variables or secure configuration files to store connection strings.
• Consider using connection pooling to improve resource management efficiency.
• Implement appropriate access controls and authentication.

🤝 Contribution

Contributions are welcome! Please refer to the project repository for details on how to contribute.

📚 Documentation

Related Projects

• MCP Protocol
• PostgreSQL Official Documentation

📄 License

Copyright © 2023 Your Name. All rights reserved.

Licensed under the following license agreement:

[TO BE ADDED]