Spark SQL

About Spark SQL

Use Spark SQL with your agent

claude mcp add spark-sql -- uvx spark-sql-mcp-server

{
  "mcpServers": {
    "spark-sql": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ]
    }
  }
}

Frequently asked questions

What is Spark SQL?

Spark SQL is an MCP (Model Context Protocol) server by aidancorrell in the Databases category. Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.

How do I connect Spark SQL to Claude, Cursor, or another MCP client?

Install Spark SQL from its pypi package (spark-sql-mcp-server) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is Spark SQL open source?

Yes — the source code is public at github.com/aidancorrell/spark-sql-mcp-server.

Can AI agents pay to use Spark SQL?

Not yet through Loomal — Spark SQL is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.