Dataproc MCP Server

A production-ready Model Context Protocol (MCP) server for Google Cloud Dataproc operations. Provides intelligent defaults, comprehensive tooling

Local serverstdioTypeScript

What is the Dataproc MCP MCP server?

A production-ready Model Context Protocol (MCP) server for Google Cloud Dataproc operations. Provides intelligent defaults, comprehensive tooling, and seamless integration with Roo (VS Code) for big data workflows. That is what the dataproc mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

  • Complete Tool Access - All 22 MCP tools available in Claude.ai
  • HTTPS Tunneling - Cloudflare tunnel for secure external access
  • OAuth Authentication - GitHub OAuth for secure authentication
  • Trusted Certificates - No browser warnings or connection issues
  • WebSocket Support - Full WebSocket compatibility with Claude.ai
  • Production Ready - Tested and verified working solution

Getting it running

@dipseth/dataproc-mcp-server on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • start_dataproc_cluster — Create and start new clusters
  • create_cluster_from_yaml — Create from YAML configuration
  • create_cluster_from_profile — Create using predefined profiles
  • list_clusters — List all clusters with filtering
  • list_tracked_clusters — List MCP-created clusters
  • get_cluster — Get detailed cluster information
  • delete_cluster — Delete existing clusters
  • get_zeppelin_url — Get Zeppelin notebook URL
  • submit_hive_query — Submit Hive queries to clusters
  • submit_dataproc_job — Submit Spark/PySpark/Presto jobs
  • cancel_dataproc_job — Cancel running or pending jobs
  • get_job_status — Get job execution status

What it needs from you

Configuration is passed through the environment: LOG_LEVEL, DATAPROC_CONFIG_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Dataproc MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Dataproc MCP's toolset — start_dataproc_cluster, create_cluster_from_yaml, create_cluster_from_profile and 11 more — is a fair guide to whether it matches your workflow. It is maintained by dipseth; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
start_dataproc_clusterCreate and start new clusters
create_cluster_from_yamlCreate from YAML configuration
create_cluster_from_profileCreate using predefined profiles
list_clustersList all clusters with filtering
list_tracked_clustersList MCP-created clusters
get_clusterGet detailed cluster information
delete_clusterDelete existing clusters
get_zeppelin_urlGet Zeppelin notebook URL
submit_hive_querySubmit Hive queries to clusters
submit_dataproc_jobSubmit Spark/PySpark/Presto jobs
cancel_dataproc_jobCancel running or pending jobs
get_job_statusGet job execution status
get_job_resultsGet job outputs and results
get_query_statusGet Hive query status

How to install the Dataproc MCP MCP server

{
  "mcpServers": {
    "dataproc": {
      "command": "npx",
      "args": ["@dipseth/dataproc-mcp-server@latest"],
      "env": {
        "LOG_LEVEL": "info"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
LOG_LEVELConfiguration value read at startup.Optional
DATAPROC_CONFIG_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Dataproc MCP to start dataproc cluster.
  • Use Dataproc MCP to create cluster from yaml.
  • Use Dataproc MCP to create cluster from profile.

Frequently asked questions

It connects Dataproc MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (start_dataproc_cluster, create_cluster_from_yaml, create_cluster_from_profile, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Dataproc MCP directly.