MSSql

The MSSQL MCP Server allows your AI assistants (MCP clients) to directly access to Microsoft SQL Server databases.

It built with Akka.NET for internal coordination and the official MCP C# SDK for protocol compliance.

Features

• 🗃️ Schema Discovery – AI agents can explore database structure without complex SQL queries
• ⚡ Full SQL Support – Execute SELECT, INSERT, UPDATE, DELETE, and DDL operations
• ✅ Connection Validation – Automatic database connectivity checks on startup
• 🛡️ Comprehensive Error Handling – Clear, actionable error messages for troubleshooting
• 📊 Table Formatting – Query results formatted in readable tables for AI consumption
• 🐳 Docker Support – Easy deployment with built-in .NET Docker tooling
• 🏗️ Akka.NET Architecture – Reliable internal coordination and state management

Use Cases

• Database Documentation Generation – AI agents can automatically discover and document database schemas, table relationships, and data structures without manual SQL scripting
• Automated Data Quality Checks – Enable AI to run validation queries, identify data inconsistencies, and generate reports on database health and integrity issues
• Dynamic Query Building – Allow AI assistants to construct and execute complex SQL queries based on natural language requests, perfect for non-technical users who need database insights
• Database Migration Assistance – AI agents can analyze existing schemas, suggest optimizations, and help plan database migrations by understanding current structure and data patterns

Configuration

The server requires one environment variable:

MSSQL_CONNECTION_STRING – Your complete SQL Server connection string

Connection String Examples:

Windows Authentication:

Server=localhost;Database=MyDatabase;Trusted_Connection=true;

SQL Server Authentication:

Server=localhost;Database=MyDatabase;User Id=myuser;Password=mypassword;

Azure SQL Database:

Server=myserver.database.windows.net;Database=mydatabase;User Id=myuser;Password=mypassword;Encrypt=true;

MCP Client Configuration

Cursor:

Add to Cursor Settings → Features → Model Context Protocol:

{
  "mcpServers": {
    "mssql": {
      "command": "docker",
      "args": [
          "run", "-i", "--rm",
          "-e", "MSSQL_CONNECTION_STRING",
          "mssql-mcp:latest"
      ],
      "env": {
          "MSSQL_CONNECTION_STRING": "Server=host.docker.internal,1533; Database=MyDb; User Id=myUser; Password=My(!)Password;TrustServerCertificate=true;"
      }
    }
  }
}

Claude Desktop:

Add to configuration file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mssql": {
      "command": "docker",
      "args": [
          "run", "-i", "--rm",
          "-e", "MSSQL_CONNECTION_STRING",
          "mssql-mcp:latest"
      ],
      "env": {
          "MSSQL_CONNECTION_STRING": "Server=host.docker.internal,1533; Database=MyDb; User Id=myUser; Password=My(!)Password;TrustServerCertificate=true;"
      }
    }
  }
}

Available Tools

• execute_sql – Execute any SQL query against the database
• list_tables – List all tables with schema, name, type, and row count
• list_schemas – List all available schemas/databases in the SQL Server instance

Docker Networking Solutions

For SQL Server on Host Machine: Use host.docker.internal instead of localhost in connection strings.

For SQL Server in Docker: Create a Docker Compose setup with custom networks:

version: '3.8'
networks:
  sql-network:
    driver: bridge
services:
  mssql-mcp:
    build: .
    environment:
      - MSSQL_CONNECTION_STRING=Server=sqlserver;Database=MyDatabase;User Id=sa;Password=YourPassword123!;
    networks:
      - sql-network
    depends_on:
      - sqlserver
  sqlserver:
    image: mcr.microsoft.com/mssql/server:2022-latest
    environment:
      - ACCEPT_EULA=Y
      - SA_PASSWORD=YourPassword123!
    networks:
      - sql-network

For Linux: Use host network mode:

docker run -it --rm --network host \
  -e MSSQL_CONNECTION_STRING="Server=localhost;Database=MyDB;User Id=sa;Password=YourPassword123!;" \
  mssql-mcp:latest

Security Best Practices

Create dedicated database users with minimal permissions:

Read-only access:

CREATE LOGIN mcp_readonly WITH PASSWORD = 'SecurePassword123!';
CREATE USER mcp_readonly FOR LOGIN mcp_readonly;
GRANT SELECT ON SCHEMA::dbo TO mcp_readonly;
GRANT VIEW DEFINITION ON SCHEMA::dbo TO mcp_readonly;

Read-write access:

CREATE LOGIN mcp_readwrite WITH PASSWORD = 'SecurePassword123!';
CREATE USER mcp_readwrite FOR LOGIN mcp_readwrite;
GRANT SELECT, INSERT, UPDATE, DELETE ON SCHEMA::dbo TO mcp_readwrite;
GRANT VIEW DEFINITION ON SCHEMA::dbo TO mcp_readwrite;

FAQs

Q: Can I connect to Azure SQL Database?
A: Yes, use a connection string with Encrypt=true parameter. The server supports all SQL Server variants including Azure SQL Database, SQL Managed Instance, and on-premises installations.

Q: How do I troubleshoot connection issues?
A: First, test your connection string with SQL Server Management Studio. For Docker deployments, use host.docker.internal instead of localhost. Check that TCP/IP is enabled in SQL Server Configuration Manager and port 1433 is accessible.

Q: Is this safe for production use?
A: The server itself is production-ready, but security depends on your configuration. Create dedicated database users with minimal required permissions, use encrypted connections, and implement proper access controls. Never use sa or admin accounts.

Q: Can I run this without Docker?
A: Yes, you can run the compiled binary directly. You’ll need .NET 9.0 runtime installed. Use the local binary configuration in your MCP client settings instead of Docker commands.

Q: How do I handle special characters in connection strings?
A: Escape special characters in passwords and use proper JSON encoding in configuration files. For Docker environment variables, consider using Docker secrets or external configuration files for complex passwords.