mcpField
S
Simple MCP MySQL Server

Simple MCP MySQL Server

Local
github.com/alexcc4Databases7Updated 85w ago

About Simple MCP MySQL Server

Simple MCP MySQL Server is a lightweight Python MCP server for AI assistants that need controlled access to MySQL. It supports read-only SQL and exposes table listings and schema details.

Key features

  1. 01List database tables
  2. 02Retrieve table schemas
  3. 03Run read-only SQL queries
  4. 04Configure access through environment variables

Use cases

  1. 01Inspect tables and columns
  2. 02Retrieve matching database records
  3. 03Aggregate and count stored data

MCP support

The MCP server exposes `mysql://schema` and `mysql://tables` resources, plus the `query_data` tool for read-only queries.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Simple MCP MySQL Server

A lightweight Model Context Protocol (MCP) server that enables secure interaction with MySQL databases. This server allows AI assistants like Claude to list tables, read data, and execute SQL queries through a controlled interface.

Features

  • List all MySQL tables in the database
  • Retrieve detailed schema information for all tables
  • Execute read-only SQL queries with proper error handling
  • Secure database access through environment variables
  • Simple configuration and deployment

Installation

# Clone the repository
git clone [email protected]:alexcc4/mcp-mysql-server.git
cd mysql-mcp-server

# Install dependencies using uv (recommended)
uv sync

Configuration

Set the following environment variables:

  • export DB_HOST=localhost # Database host
  • export DB_PORT=3306 # Database port (defaults to 3306 if not specified)
  • export DB_USER=your_username # Database username
  • export DB_PASSWORD=your_password # Database password
  • export DB_NAME=your_database # Database name

Usage

Manual Start
uv run main.py
With Claude Desktop

Add this to your Claude Desktop configuration file:

Mac Claude Desktop config: ~/Library/Application Support/Claude/claude_desktop_config.json (create it if it doesn't exist)

{
    "mcpServers": {
        "sql": {
            "command": "/path/uv",
            "args": [
                "--directory",
                "code_path",
                "run",
                "main.py"
            ],
            "env": {
                "DB_HOST": "127.0.0.1",
                "DB_PORT": "3306",
                "DB_USER": "your_user",
                "DB_PASSWORD": "your_password",
                "DB_NAME": "your_database"
           }
        }
    }
}
Example Queries

Once configured, you can ask Claude questions like:

"Show me all tables in the database"
"Top 10 rows from users table"
"Find all orders placed in the last 30 days"
"Count of users by country"
"Show me the schema of the products table"

Available Resources

The server provides the following resources:

  • mysql://schema - Complete database structure information including all tables and columns
  • mysql://tables - List of all tables in the database

Available Tools

The server provides the following tools:

  • query_data - Execute read-only SQL queries and return results

Requirements

  • uv (recommended)
  • Python 3.12.2+
  • MySQL server

Security Considerations

  • Use a database user with minimal required permissions (read-only)
  • Never use root credentials for production environments
  • Consider implementing query whitelisting for sensitive databases
  • Monitor and log all database operations

License

MIT

Reference

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.