datacloud_serverless-spark_toolbox

Provides access to DataCloud's serverless Spark toolbox for big data processing, Spark jobs, and SQL queries. Runs locally as stdio subprocess, requires SERVERLESS_SPARK_PROJECT and SERVERLESS_SPARK_LOCATION env vars.

data-engineering

npx claudepluginhub gemini-cli-extensions/data-agent-kit-starter-pack --plugin data-agent-kit-starter-pack

Add to Your Project

Add to your .mcp.json:

{
  "mcpServers": {
    "datacloud_serverless-spark_toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server@>=1.1.0",
        "--prebuilt",
        "serverless-spark",
        "--stdio",
        "--user-agent-metadata",
        "datacloud.claude"
      ],
      "env": {
        "SERVERLESS_SPARK_PROJECT": "",
        "SERVERLESS_SPARK_LOCATION": ""
      }
    }
  }
}

Security Considerations

External connections

This server connects to external services. Review the URLs it accesses before enabling.

Details

Commandnpx

Access Levelwrite

Arguments

-y@toolbox-sdk/server@>=1.1.0--prebuiltserverless-spark--stdio--user-agent-metadatadatacloud.claude

Environment Variables

SERVERLESS_SPARK_PROJECT=

SERVERLESS_SPARK_LOCATION=

Actions

Plugins (1)

data-agent-kit-starter-pack30