mcpField
M
MySQL MCP Server

MySQL MCP Server

Local
github.com/kevinwattDatabases18Updated 87w ago
Repository

About MySQL MCP Server

MySQL MCP Server gives LLMs MCP-based access to MySQL databases, covering read-only queries and data modifications. Parameterized queries, transaction handling, and query and result limits govern database access.

Key features

  1. 01Run read-only SELECT queries
  2. 02Insert, update, and delete data
  3. 03List tables and inspect schemas
  4. 04Parameterized SQL queries
  5. 05Transactions and query limits
  6. 06Performance monitoring and logging

Use cases

  1. 01Review database tables and structures
  2. 02Query records matching criteria
  3. 03Modify database records with SQL
  4. 04Limit query size and execution time

MCP support

The MCP server provides MCP clients with the mysql_query, mysql_execute, list_tables, and describe_table tools for querying and modifying MySQL databases.

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "mysql": {
      "command": "npx",
      "args": [
        "-y",
        "@kevinwatt/mysql-mcp"
      ]
    }
  }
}
Run commandnpx -y @kevinwatt/mysql-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@kevinwatt/mysql-mcp

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
sqlstringYesSQL SELECT query to execute

Details

From the project README

MySQL MCP Server

An MCP server implementation that integrates with MySQL databases, providing secure database access capabilities for LLMs.

Features

  • Read Operations
    • Execute read-only SELECT queries
    • List all database tables
    • Show table structures
    • View schema information
  • Write Operations
    • Execute INSERT/UPDATE/DELETE with transaction support
    • Parameterized queries for data safety
    • Returns affected rows and insert IDs
  • Security
    • Read-only transaction mode for SELECT queries
    • Query length and result size limits
    • Performance monitoring and logging
    • Automatic transaction handling

Installation

npm install -g @kevinwatt/mysql-mcp

Usage with Dive Desktop

  1. Click "+ Add MCP Server" in Dive Desktop
  2. Copy and paste this configuration:
{
  "mcpServers": {
    "mysql": {
      "command": "npx",
      "args": [
        "-y",
        "@kevinwatt/mysql-mcp"
      ],
      "env": {
        "MYSQL_HOST": "127.0.0.1",
        "MYSQL_PORT": "3306",
        "MYSQL_USER": "root",
        "MYSQL_PASS": "",
        "MYSQL_DB": "your_database"
      }
    }
  }
}
  1. Click "Save" to install the MCP server

Tool Documentation

  • mysql_query

    • Execute read-only SELECT queries
    • Inputs:
      • sql (string): SQL SELECT query to execute
    • Limits:
      • Maximum query length: 4096 characters
      • Maximum result rows: 1000
      • Query timeout: 30 seconds

  • mysql_execute

    • Execute data modification operations
    • Inputs:
      • sql (string): SQL statement (INSERT/UPDATE/DELETE)
      • params (array, optional): Parameters for the SQL statement
    • Features:
      • Returns affected rows count
      • Returns last insert ID
      • Automatic transaction handling

  • list_tables

    • List all tables in current database
    • No inputs required

  • describe_table

    • Show table structure
    • Inputs:
      • table (string): Table name to describe

Usage Examples

Ask your LLM to:

"Show me all tables in the database"
"Describe the structure of users table"
"Select all active users from the database"
"Insert a new record into orders table"

Manual Start

If needed, start the server manually:

npx @kevinwatt/mysql-mcp

Requirements

  • Node.js 18+
  • MySQL Server
  • MCP-compatible LLM service

License

MIT

Author

Dewei Yen

Keywords

  • mcp
  • mysql
  • database
  • dive
  • llm
  • ai

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.