PostgreSQL MCP Server

An MCP server that exposes PostgreSQL database operations as tools for AI assistants.

What is MCP?

Model Context Protocol (MCP) connects AI assistants to external tools and data. This server lets AI assistants execute SQL queries and inspect your PostgreSQL database schema.

Setup

1. Install Dependencies

Note: This project uses Poetry for dependency management. If you don't have Poetry installed, you can install it with:

curl -sSL https://install.python-poetry.org | python3 -

See the official Poetry documentation for alternative installation methods.

poetry install

2. Configure Database

Copy .env.example to .env and add your PostgreSQL credentials:

cp .env.example .env

Edit .env:

DB_NAME=your_database
DB_USER=postgres
DB_PASSWORD=your_password
DB_HOST=localhost
DB_PORT=5432

Testing

MCP Inspector (Recommended)

npx @modelcontextprotocol/inspector poetry run python postgres-mcp-server/main.py

This opens a web UI where you can:

• View available tools under the Tools tab

• Test get_schema

• See real-time results

Quick Test

poetry run python postgres-mcp-server/main.py

Press Ctrl+C to stop. No errors = working correctly.

Available Tools

get_schema() - Get database schema

Connect to Cursor

Add to your Cursor MCP config (global settings):

{
  "mcpServers": {
    "postgres": {
      "command": "poetry",
      "args": ["-C", "/absolute/path/to/postgres-mcp-server", "run", "python", "postgres-mcp-server/main.py"]
    }
  }
}

Replace /absolute/path/to/postgres-mcp-server with your actual project path.

Future Proof Data Science - Teaching data scientists to optimize workflows with AI