datasource-mcp
MySQL datasource MCP server for AI clients like Cursor and Claude Desktop, enabling SQL query execution via natural language.
README
datasource-mcp
MySQL datasource MCP server for AI clients (Cursor, Claude Desktop, etc.).
Database Support: Currently supports MySQL only. Support for PostgreSQL, SQLite, and other databases is planned for future releases.
Install
pip install datasource-mcp
If the package is not yet available on your PyPI mirror, use the official index:
pip install datasource-mcp -i https://pypi.org/simple/
Or run without installing (requires uv):
uvx datasource-mcp
Note:
uvx datasource-mcpdownloads the package and immediately starts the MCP stdio server. It will block the terminal while waiting for a client connection. Configure it in your MCP client instead of running it manually.
Cursor / MCP Client Config
Option 1: pip install (local environment)
Run pip install datasource-mcp first, then add this to mcp.json:
{
"mcpServers": {
"datasource-mcp": {
"command": "datasource-mcp",
"env": {
"DB_HOST": "127.0.0.1",
"DB_PORT": "3306",
"DB_USER": "root",
"DB_PASSWORD": "your_password",
"DB_NAME": "your_database"
}
}
}
}
Option 2: uvx without installing (recommended)
No pip install required — uvx fetches the package from PyPI and runs it automatically. Requires uv to be installed.
{
"mcpServers": {
"datasource-mcp": {
"command": "uvx",
"args": ["datasource-mcp"],
"env": {
"DB_HOST": "127.0.0.1",
"DB_PORT": "3306",
"DB_USER": "root",
"DB_PASSWORD": "your_password",
"DB_NAME": "your_database"
}
}
}
}
After updating the config, click Refresh in the MCP panel to apply changes.
Environment Variables
| Variable | Default | Description |
|---|---|---|
DB_HOST |
127.0.0.1 |
MySQL host |
DB_PORT |
3306 |
MySQL port |
DB_USER |
root |
MySQL user |
DB_PASSWORD |
root |
MySQL password |
DB_NAME |
aix |
Database name |
DB_CONNECT_TIMEOUT |
5 |
Connection timeout (seconds) |
Tools
db_exe
Execute SQL and return a JSON string:
{"success": true, "row_count": 1, "truncated": false, "rows": [...]}
Error response:
{"success": false, "error": "error message"}
Local Development
uv sync
uv run datasource-mcp
# or
uv run python -m datasource_mcp
Requires Python >= 3.11.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.