klogins-hash/mcp-database-server

MCP Database Server

A Model Context Protocol (MCP) server that provides database connectivity and querying capabilities via HTTP API. Optimized for deployment on Railway with Docker.

Features

• 🐘 Connect to PostgreSQL databases (DigitalOcean, AWS RDS, etc.)
• 🔍 Execute SQL queries with parameterized support
• 📋 List database tables and schemas
• 📊 Describe table structures and columns
• 📈 Retrieve table data with pagination
• 🔒 Secure SSL connections
• 🚀 Docker-optimized for Railway deployment
• 💚 Health check endpoints
• 🌐 RESTful HTTP API

Quick Deploy to Railway

Option 1: Deploy from GitHub (Recommended)

1. Fork this repository to your GitHub account

2. Connect to Railway:

   • Go to Railway
   • Click "Deploy from GitHub repo"
   • Select your forked repository
   • Railway will automatically detect the Dockerfile

3. Set Environment Variables in Railway dashboard:

   DB_USER=your_database_user
   DB_PASSWORD=your_database_password
   DB_HOST=your_database_host
   DB_PORT=your_database_port
   DB_NAME=your_database_name
   

4. Deploy - Railway will automatically build and deploy your Docker container

Option 2: Railway CLI

1. Clone and navigate to the repository:

   git clone <your-repo-url>
   cd mcp-database-server
   

2. Login to Railway:

   railway login
   

3. Initialize and deploy:

   railway init
   railway up
   

Local Development

Prerequisites

• Node.js 18+
• PostgreSQL database access

Setup

1. Install dependencies:

   npm install
   

2. Environment setup:

   cp .env.example .env
   # Edit .env with your database credentials
   

3. Run the server:

   npm start        # Production mode
   npm run dev      # Development mode with auto-reload
   npm run mcp      # MCP stdio mode
   

4. Test the API:

   curl http://localhost:3000/health
   curl http://localhost:3000/tables
   

API Endpoints

GET /

Server information and available endpoints

GET /health

Health check endpoint (used by Railway)

GET /tools

List all available MCP tools

POST /query

Execute a SQL query on the connected database.

Body:

{
  "query": "SELECT * FROM users WHERE id = $1",
  "params": ["123"]
}

GET /tables

List all tables in the database

GET /tables/:tableName

Get the structure of a specific table

GET /tables/:tableName/data?limit=100

Get data from a specific table with optional limit

MCP Tools (when using stdio mode)

query_database

Execute a SQL query on the connected database.

Parameters:

• query (string, required): SQL query to execute
• params (array, optional): Parameters for parameterized queries

list_tables

List all tables in the database.

describe_table

Get the structure of a specific table.

Parameters:

• table_name (string, required): Name of the table to describe

get_table_data

Get data from a specific table with optional limit.

Parameters:

• table_name (string, required): Name of the table
• limit (number, optional): Maximum number of rows to return (default: 100)

Environment Variables

Security Notes

• The server uses SSL connections to the database
• Parameterized queries are supported to prevent SQL injection
• Environment variables are used for sensitive credentials
• Never commit .env files to version control
• The Docker container runs as a non-root user

Docker

The application is containerized with Docker for easy deployment:

# Build the image
docker build -t mcp-database-server .

# Run the container
docker run -p 3000:3000 \
  -e DB_PASSWORD=your_password \
  mcp-database-server

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test locally
5. Submit a pull request

License

MIT License - see LICENSE file for details.