pyspark mcp for Cursor

io.github.annasmazhar/pyspark-mcp

SQL to PySpark conversion, AWS Glue job generation, and Spark code optimization.

client:Cursor transport:stdio runtime:pypi

Install pyspark mcp in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

{
  "mcpServers": {
    "pyspark-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pyspark-tools"
      ]
    }
  }
}

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs