MySQL
Interact with and manage MySQL databases. Requires connection details configured via environment variables.
MySQL MCP Server
An MCP server for interacting with MySQL databases.
This server supports executing read-only queries (query) and write queries that are ultimately rolled back (test_execute).
Setup
Environment Variables
Add the following environment variables to ~/.mcp/.env:
MYSQL_HOST=host.docker.internal # Hostname to access host services from Docker container
MYSQL_PORT=3306
MYSQL_USER=root
MYSQL_PASSWORD=your_password
Note:
host.docker.internalis a special DNS name for accessing host machine services from Docker containers. Use this setting when connecting to a MySQL server running on your host machine. If connecting to a different MySQL server, change to the appropriate hostname.
mcp.json Configuration
{
"mcpServers": {
"mysql": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--add-host=host.docker.internal:host-gateway",
"--env-file",
"/Users/username/.mcp/.env",
"ghcr.io/xiangma9712/mcp/mysql"
]
}
}
}
Usage
Starting the Server
docker run -i --rm --add-host=host.docker.internal:host-gateway --env-file ~/.mcp/.env ghcr.io/xiangma9712/mcp/mysql
Note: If you're using OrbStack,
host.docker.internalis automatically supported, so the--add-hostoption can be omitted. While Docker Desktop also typically supports this automatically, adding the--add-hostoption is recommended for better reliability.
Available Commands
1. Execute Read-only Query
{
"type": "query",
"payload": {
"sql": "SELECT * FROM your_table"
}
}
Response:
{
"success": true,
"data": [
{
"id": 1,
"name": "example"
}
]
}
2. Test Query Execution
{
"type": "test_execute",
"payload": {
"sql": "UPDATE your_table SET name = 'updated' WHERE id = 1"
}
}
Response:
{
"success": true,
"data": "The UPDATE SQL query can be executed."
}
3. List Tables
{
"type": "list_tables"
}
Response:
{
"success": true,
"data": ["table1", "table2", "table3"]
}
4. Describe Table
{
"type": "describe_table",
"payload": {
"table": "your_table"
}
}
Response:
{
"success": true,
"data": [
{
"Field": "id",
"Type": "int(11)",
"Null": "NO",
"Key": "PRI",
"Default": null,
"Extra": ""
},
{
"Field": "name",
"Type": "varchar(255)",
"Null": "YES",
"Key": "",
"Default": null,
"Extra": ""
}
]
}
Implementation Details
- Implemented in TypeScript
- Uses mysql2 package
- Runs as a Docker container
- Accepts JSON commands through standard input
- Returns JSON responses through standard output
- Uses
host.docker.internalto connect to host MySQL (compatible with both OrbStack and Docker Desktop)
Security Considerations
- Uses environment variables for sensitive information management
- SQL injection prevention is the implementer's responsibility
- Proper network configuration required for production use
- Appropriate firewall settings needed when connecting to host machine services
Related Servers
Hydrolix
Hydrolix time-series datalake integration providing schema exploration and query capabilities to LLM-based workflows.
Drug Gene Interaction Database (DGIdb)
A bridge to the Drug Gene Interaction Database (DGIdb) API, enabling AI clients to query drug-gene interaction data.
Ashare-MCP
A stock market data service for querying A-share market data from Sina and Tencent Finance.
Doris-MCP-Lite
A lightweight MCP server for connecting to Apache Doris and other MySQL-compatible databases, providing tools and prompts for LLM applications.
Graphiti MCP Server
A framework for building and querying temporally-aware knowledge graphs for AI agents.
Microsoft SQL Server
A Model Context Protocol (MCP) server for connecting to and querying Microsoft SQL Server databases.
Financial Datasets
Stock market API made for AI agents
Database
Universal database MCP server supporting multiple database types including PostgreSQL, Redshift, CockroachDB, MySQL, RDS MySQL, Microsoft SQL Server, BigQuery, Oracle DB, and SQLite
Couchbase
Interact with the data stored in Couchbase clusters using natural language.
Binance Cryptocurrency MCP
Access real-time Binance cryptocurrency market data, including prices, order books, and trading history.