Skip to content
mcp/harbor
Grok

Spark SQL for Grok

io.github.aidancorrell/spark-sql-mcp-server

Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.

client:Grok transport:stdio runtime:pypi

Install Spark SQL in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "<SPARK_HOST>",
        "SPARK_PORT": "<SPARK_PORT>",
        "SPARK_DATABASE": "<SPARK_DATABASE>",
        "SPARK_AUTH": "<SPARK_AUTH>",
        "SPARK_USERNAME": "<SPARK_USERNAME>",
        "SPARK_PASSWORD": "<SPARK_PASSWORD>",
        "SPARK_KERBEROS_SERVICE_NAME": "<SPARK_KERBEROS_SERVICE_NAME>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

Spark SQL in other clients

Spark SQL MCP server