MySQL DB
An MCP server for integrating with and managing MySQL databases.
mysqldb-mcp-server MCP server
A MySQL database MCP server project.
Installation
You can install the package using uv:
uv pip install mysqldb-mcp-server
Or using pip:
pip install mysqldb-mcp-server
Components
Tools
The server provides two tools:
-
connect_database: Connects to a specific MySQL databasedatabaseparameter: Name of the database to connect to (string)- Returns a confirmation message when connection is successful
-
execute_query: Executes MySQL queriesqueryparameter: SQL query/queries to execute (string)- Returns query results in JSON format
- Multiple queries can be sent separated by semicolons
Configuration
The server uses the following environment variables:
MYSQL_HOST: MySQL server address (default: "localhost")MYSQL_USER: MySQL username (default: "root")MYSQL_PASSWORD: MySQL password (default: "")MYSQL_DATABASE: Initial database (optional)MYSQL_READONLY: Read-only mode (set to 1/true to enable, default: false)
Quickstart
Installation
Claude Desktop
MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Development/Unpublished Server Configuration
{
"mcpServers": {
"mysqldb-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/Users/burakdirin/Projects/mysqldb-mcp-server",
"run",
"mysqldb-mcp-server"
],
"env": {
"MYSQL_HOST": "localhost",
"MYSQL_USER": "root",
"MYSQL_PASSWORD": "password",
"MYSQL_DATABASE": "[optional]",
"MYSQL_READONLY": "true"
}
}
}
}
Published Server Configuration
{
"mcpServers": {
"mysqldb-mcp-server": {
"command": "uvx",
"args": [
"mysqldb-mcp-server"
],
"env": {
"MYSQL_HOST": "localhost",
"MYSQL_USER": "root",
"MYSQL_PASSWORD": "password",
"MYSQL_DATABASE": "[optional]",
"MYSQL_READONLY": "true"
}
}
}
}
Installing via Smithery
To install MySQL Database Integration Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @burakdirin/mysqldb-mcp-server --client claude
Development
Building and Publishing
To prepare the package for distribution:
- Sync dependencies and update lockfile:
uv sync
- Build package distributions:
uv build
This will create source and wheel distributions in the dist/ directory.
- Publish to PyPI:
uv publish
Note: You'll need to set PyPI credentials via environment variables or command flags:
- Token:
--tokenorUV_PUBLISH_TOKEN - Or username/password:
--username/UV_PUBLISH_USERNAMEand--password/UV_PUBLISH_PASSWORD
Debugging
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /Users/burakdirin/Projects/mysqldb-mcp-server run mysqldb-mcp-server
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
Похожие серверы
cowork-semantic-search
Local semantic search over documents (txt, md, pdf, docx, pptx, csv). Fully offline, multilingual, hybrid vector + keyword search via LanceDB. No API keys, no cloud.
CData SAP Netweaver Gateway
Connect to SAP Netweaver Gateway data using CData's MCP Server. Requires a separately licensed CData JDBC Driver.
Intacct MCP Server by CData
A read-only MCP server for Intacct, enabling LLMs to query live data using the CData JDBC Driver.
Flexpa FHIR
An MCP server for interacting with FHIR (Fast Healthcare Interoperability Resources) servers, enabling access and search of healthcare data.
VictoriaMetrics MCP Server
Access VictoriaMetrics APIs for monitoring, observability, and debugging.
MCP MySQL Server
An MCP server based on Spring AI that executes arbitrary SQL queries against a configured MySQL database.
GraphDB
Provides read-only access to an Ontotext GraphDB repository.
Weaviate MCP Client
An MCP client for connecting to and interacting with a Weaviate vector database.
HowToCook
A recipe database server providing meal planning, recipe recommendations, and menu suggestions for daily meals.
QMT MCP Server
Download and query stock market data using the QMT platform.