HotStack

← Back to browse

Spark SQL

Indexed by io.github.aidancorrell
View source ↗

About

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

Use this server

Add it to your MCP client. The catalogue lists this config verbatim from its source — it does not run, download, or vouch for the server. Review the command before you run it.

Transportstdio (runs a local command)
Env varsSPARK_HOST SPARK_PORT SPARK_DATABASE SPARK_AUTH SPARK_USERNAME SPARK_PASSWORD SPARK_KERBEROS_SERVICE_NAME
Claude Code 
claude mcp add --env SPARK_HOST= --env SPARK_PORT= --env SPARK_DATABASE= --env SPARK_AUTH= --env SPARK_USERNAME= --env SPARK_PASSWORD= --env SPARK_KERBEROS_SERVICE_NAME= spark-sql-mcp-server -- uvx spark-sql-mcp-server
Cursor

Add to Cursor

If the button doesn't open Cursor, use the JSON below — Cursor accepts the same mcpServers config.

VS Code 
code --add-mcp '{"name":"spark-sql-mcp-server","command":"uvx","args":["spark-sql-mcp-server"],"env":{"SPARK_HOST":"","SPARK_PORT":"","SPARK_DATABASE":"","SPARK_AUTH":"","SPARK_USERNAME":"","SPARK_PASSWORD":"","SPARK_KERBEROS_SERVICE_NAME":""}}'
JSON 
{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "command": "uvx",
      "args": [
        "spark-sql-mcp-server"
      ],
      "env": {
        "SPARK_HOST": "",
        "SPARK_PORT": "",
        "SPARK_DATABASE": "",
        "SPARK_AUTH": "",
        "SPARK_USERNAME": "",
        "SPARK_PASSWORD": "",
        "SPARK_KERBEROS_SERVICE_NAME": ""
      }
    }
  }
}

Environment variables are listed by name only — fill in your own values. Entries never carry secrets.