MCP ExplorerExplorer

Mysql Mcp Server

@SuMiaoALion 17 days ago
1 MIT
FreeCommunity
AI Systems
A general Mysql-MCP-Server

Overview

What is Mysql Mcp Server

mysql-mcp-server is a Model Context Protocol (MCP) server designed to provide secure MySQL database operations for AI assistants and other MCP clients.

Use cases

Use cases include integrating with AI assistants for data retrieval and manipulation, providing a secure backend for applications that require database access, and serving as a middleware for data operations in machine learning workflows.

How to use

To use mysql-mcp-server, install it via npm with the command ‘npm install mysql-mcp-server’. Configure it using environment variables for MySQL connection details, and integrate it with MCP clients like Claude Desktop by adding the necessary configuration in the respective JSON file.

Key features

Key features include executing safe SQL queries (SELECT, INSERT, SHOW, DESCRIBE), retrieving detailed table structure information, convenient data insertion with automatic parameterization, and listing all tables in the database. It also offers security features like SQL injection protection and automatic LIMIT clauses.

Where to use

mysql-mcp-server can be used in various fields that require secure database interactions, particularly in AI applications, data analysis, and any environment where MCP clients operate.

Content

MySQL MCP Server

A Model Context Protocol (MCP) server that provides secure MySQL database operations for AI assistants and other MCP clients.

Features

🛠️ Tools

  • execute_query - Execute safe SQL queries (SELECT, INSERT, SHOW, DESCRIBE)
  • get_table_info - Get detailed table structure information
  • insert_data - Convenient data insertion with automatic parameterization
  • list_tables - List all tables in the database

📊 Resources

  • Database Info (mysql://database/info) - Database metadata and table list
  • Table Structure (mysql://table/{table_name}) - Detailed table schema information

🔒 Security Features

  • Limited Operations: Only allows safe operations (SELECT, INSERT, SHOW, DESCRIBE)
  • SQL Injection Protection: Uses parameterized queries
  • Automatic LIMIT: Adds LIMIT clauses to SELECT queries to prevent large data dumps
  • Connection Pooling: Efficient database connection management

Installation

npm install mysql-mcp-server

Configuration

The server can be configured using environment variables:

Variable Default Description
MYSQL_HOST localhost MySQL server hostname
MYSQL_PORT 3306 MySQL server port
MYSQL_USER root MySQL username
MYSQL_PASSWORD (empty) MySQL password
MYSQL_DB mysql Default database name
MYSQL_TIMEZONE +00:00 MySQL timezone

Usage with MCP Clients

Claude Desktop

Add to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "mysql": {
      "command": "npx",
      "args": [
        "mysql-mcp-server"
      ],
      "env": {
        "MYSQL_HOST": "your-mysql-host",
        "MYSQL_PORT": "3306",
        "MYSQL_USER": "your-username",
        "MYSQL_PASSWORD": "your-password",
        "MYSQL_DB": "your-database"
      }
    }
  }
}

Other MCP Clients

For other MCP clients, use the server with stdio transport:

npx mysql-mcp-server

Development

Prerequisites

  • Node.js 18+
  • TypeScript
  • Access to a MySQL database

Setup

  1. Clone the repository:
git clone https://github.com/your-username/mysql-mcp-server.git
cd mysql-mcp-server
  1. Install dependencies:
npm install
  1. Set up environment variables:
cp .env.example .env
# Edit .env with your database configuration
  1. Build the server:
npm run build

Development Commands

# Build the server
npm run build

# Watch mode for development
npm run watch

# Debug with MCP Inspector
npm run inspector

Testing

You can test the server using the MCP Inspector:

npm run inspector

This will start the inspector and provide a URL to test the server in your browser.

Example Usage

Once connected through an MCP client, you can:

  1. List all tables:

    Use the list_tables tool
    
  2. Get table structure:

    Use get_table_info with table_name: "users"
    
  3. Query data:

    Use execute_query with sql: "SELECT * FROM users LIMIT 10"
    
  4. Insert data:

    Use insert_data with table_name: "users" and data: {"name": "John", "email": "[email protected]"}
    

Security Considerations

This server is designed with security in mind:

  • Read-mostly operations: Only SELECT, INSERT, SHOW, and DESCRIBE operations are allowed
  • No destructive operations: UPDATE and DELETE are explicitly forbidden
  • Parameterized queries: All user inputs are properly escaped
  • Connection limits: Uses connection pooling to prevent resource exhaustion
  • Query limits: Automatic LIMIT clauses prevent large data dumps

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see LICENSE file for details.

Related

Tools

No tools

Comments