📌Overview

Purpose: Enables secure interaction with Microsoft SQL Server databases for AI assistants through a structured interface.

Overview: The Microsoft SQL Server MCP Server facilitates safe and organized database exploration and analysis by allowing AI assistants to list tables, read data, and execute SQL queries. It emphasizes security by employing environment variables for access control and provides comprehensive logging features.

Key Features:

List Available Tables: Enables the listing of SQL Server tables, providing a glance at available resources for further exploration.
Data Reading: Allows access to table contents, facilitating data retrieval for analysis and reporting.
Query Execution: Supports the execution of SQL queries with robust error handling, enhancing the reliability of database interactions.
Secure Access: Utilizes environment variables to safeguard database credentials and minimize exposure to risks.
Comprehensive Logging: Maintains detailed logs of database operations, crucial for monitoring and auditing purposes.
Automatic Dependency Installation: Simplifies installation by automatically handling required system dependencies, such as FreeTDS.

Microsoft SQL Server MCP Server

A Model Context Protocol (MCP) server that enables 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, making database exploration and analysis safer and more structured.

Features

List available SQL Server tables as resources
Read table contents
Execute SQL queries with proper error handling
Secure database access through environment variables
Comprehensive logging
Automatic system dependency installation

Installation

The package will automatically install required system dependencies (like FreeTDS) when installed through MCP:

pip install mssql-mcp-server

Configuration

Set the following environment variables:

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

Usage

With Claude Desktop

Add this to your claude_desktop_config.json:

{
  "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"
      }
    }
  }
}

As a standalone server

# Install dependencies
pip install -r requirements.txt

# Run the server
python -m mssql_mcp_server

Development

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

# Create 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 Considerations

Never commit environment variables or credentials
Use a database user with minimal required permissions
Consider implementing query whitelisting for production use
Monitor and log all database operations

Security Best Practices

This MCP server requires database access to function. For security:

Create a dedicated SQL Server login with minimal permissions
Never use sa credentials or administrative accounts
Restrict database access to only necessary operations
Enable logging for audit purposes
Regular security reviews of database access

See SQL Server Security Configuration Guide for detailed instructions on creating a restricted SQL Server login, setting appropriate permissions, monitoring database access, and security best practices.

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

License

MIT License - see LICENSE file for details.

Contributing

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request