datasource-mcp
Provides tools for executing SQL queries against a MySQL database, returning results as JSON.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@datasource-mcp Show me the top 10 customers by total spending"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-mcpIf 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-mcpNote:
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.
Related MCP server: MySQL MCP Server
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 |
|
| MySQL host |
|
| MySQL port |
|
| MySQL user |
|
| MySQL password |
|
| Database name |
|
| 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_mcpRequires Python >= 3.11.
Available Tools
1 tooldb_exeB
执行 SQL 并返回 JSON 字符串结果。
Inputs: sql (required), max_rows. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no ambiguity in tool selection. The tool's description clearly states it executes SQL and returns JSON.
A single tool name, db_exe, follows snake_case and is understandable, but it lacks a clear verb_noun pattern. However, consistency is not an issue with only one tool.
The server has only one tool, which is too few for a datasource MCP server. Its apparent scope would typically require multiple tools for connection management, schema inspection, and querying.
The tool surface is severely limited; it only executes SQL. There are no tools to list tables, describe schemas, or manage data sources, causing significant gaps for agents.
Maintenance
Related MCP Connectors
Hosted MySQL MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
Hosted SQL Server MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server that allows Claude AI to interact directly with MySQL databases, enabling query execution and table information retrieval through natural language.14ISC
- AlicenseNot gradedqualityDmaintenanceA MySQL MCP server for secure database interaction, enabling schema inspection, query execution, and RBAC via AI coding assistants.7MIT
- AlicenseBqualityCmaintenanceMCP server that connects AI agents to MySQL databases for schema exploration, data querying, and SQL execution via natural language.722 PyPI2MIT
- AlicenseNot gradedqualityDmaintenanceA production-ready MCP server for MySQL database integration with AI agents, enabling database exploration, CRUD operations, schema management, and performance monitoring through natural language.MIT