Microsoft SQL Server MCP Server

🚀 Microsoft SQL Server MCP Server

A Model Context Protocol (MCP) server designed to enable secure interaction with Microsoft SQL Server databases. This server allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, ensuring safer and more organized database exploration and analysis.

🚀 Quick Start

The MCP server provides a secure way to interact with Microsoft SQL Server databases. It allows AI assistants to perform various operations on the database in a controlled manner.

✨ Features

• List available SQL Server tables: Manage them as resources.
• Read table contents.
• Execute SQL queries: With comprehensive error handling.
• Secure access via environment variables: Ensure the security of database connections.
• Comprehensive logging: Track all operations.
• Automatically install system dependencies.

📦 Installation

When installing via MCP, the required system dependencies (such as FreeTDS) will be automatically configured:

pip install mssql-mcp-server

📚 Documentation

Configuration Guide

Set the following environment variables to configure the database connection:

MSSQL_SERVER=localhost
MSSQL_USER=your_username
MSSQL_PASSWORD=your_password
MSSQL_DATABASE=your_database

Usage Examples

Integration with Claude Desktop

Add the following content to the claude_desktop_config.json file:

{
  "mcpServers": {
    "mssql": {
      "command": "uv",
      "args": [
        "--directory", 
        "path/to/mssql_mcp_server",
        "run",
        "mssql_mcp_server"
      ],
      "env": {
        "MSSQL_SERVER": "localhost",
        "MSSQL_USER": "your_username",
        "MSSQL_PASSWORD": "your_password",
        "MSSQL_DATABASE": "your_database"
      }
    }
  }
}

Run as an Independent Server

# Install dependencies
pip install -r requirements.txt

# Start the server
python -m mssql_mcp_server

Development Guide

# Clone the repository
git clone https://github.com/RichardHan/mssql_mcp_server.git
cd mssql_mcp_server

# Create a virtual environment
python -m venv venv
source venv/bin/activate  # Or `venv\Scripts\activate` on Windows

# Install development dependencies
pip install -r requirements-dev.txt

# Run tests
pytest

Security Precautions

• Avoid committing environment variables or credentials to the version control system.
• Use a database user with limited permissions.
• Implement a query whitelist mechanism in the production environment.
• Monitor and log all database operations.

Security Best Practices

This MCP server requires database access privileges to function properly. To ensure security:

1. Create a dedicated SQL Server login and grant the minimum necessary permissions.
2. Avoid using sa credentials or other administrative accounts.
3. Limit database access privileges to only necessary operations.
4. Enable logging for auditing purposes.
5. Conduct regular security reviews for database access.

Refer to the SQL Server Security Configuration Guide for detailed instructions, including:

• How to create a restricted SQL Server login.
• Set appropriate permissions.
• Monitor database access.
• Security best practices.

⚠️ Important Note

Always follow the principle of least privilege when configuring database access.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

🤝 Contribution Guide

1. Fork the repository.
2. Create a feature branch (e.g., git checkout -b feature/amazing-feature).
3. Commit your changes (e.g., git commit -m 'Add an amazing feature').
4. Push to the branch (e.g., git push origin feature/amazing-feature).
5. Submit a Pull Request.

By following these steps, you can contribute to this project.