# Managed Service for Apache Spark MCP
> Google Cloud managed MCP server for Managed Service for Apache Spark. Exact tool names and accessible operations depend on the published server reference and configured Google Cloud permissions.
Canonical: https://www.mcpfolio.com/servers/google-cloud-managed-service-for-apache-spark
Last updated: 2026-10-28
## Catalog record

- Publisher: Google Cloud
- Categories: cloud-service

## Website

https://docs.cloud.google.com/dataproc/docs/reference/mcp

## Transports

Streamable HTTP

## Authentication

Google Cloud authentication: OAuth 2.0 using Application Default Credentials (ADC) in supported Google clients, or a client OAuth ID/secret or bearer token in compatible third-party clients. The principal needs mcp.tools.call plus the underlying product permissions; API key authentication is only available for services that explicitly support it.

## Tools

- **list_clusters**: List Dataproc clusters in a Google Cloud project
- **get_cluster**: Get a Dataproc cluster in a Google Cloud project
- **create_cluster**: Create a Dataproc cluster in a Google Cloud project
- **delete_cluster**: Delete a Dataproc cluster in a Google Cloud project
- **list_jobs**: List Dataproc jobs in a Google Cloud project
- **get_job**: Get a Dataproc job in a Google Cloud project
- **list_batches**: List Dataproc batches in a Google Cloud project
- **get_batch**: Get a Dataproc batch in a Google Cloud project
- **create_batch**: Create a Dataproc Batch in a Google Cloud project
- **delete_batch**: Delete a Dataproc Batch in a Google Cloud project
- **list_sessions**: List Dataproc Sessions in a Google Cloud project
- **get_session**: Get a Dataproc session in a Google Cloud project
- **create_session**: Create a Dataproc Session in a Google Cloud project
- **delete_session**: Delete a Dataproc Session in a Google Cloud project
- **get_operation**: Gets the status of a long-running operation. Usage Some tools (for example, create_cluster and delete_cluster ) return a long-running operation. You can use this tool to get the status of the operation. It can be called repeatedly to poll the status of a long running operation Parameters * name : The name of the operation to get. * name should be the name returned by the tool that initiated the operation. * name should be in the format of projects/{project}/locations/{location}/operations/{operation} .

## Sources

- [official_tool_reference](https://docs.cloud.google.com/dataproc/docs/reference/mcp)
- [official_server_catalog](https://docs.cloud.google.com/mcp/supported-products)
- [official_setup_guide](https://docs.cloud.google.com/mcp/configure-mcp-ai-application)
- [official_authentication_guide](https://docs.cloud.google.com/mcp/authenticate-mcp)
- [official_source](https://docs.cloud.google.com/managed-spark/docs/reference/mcp)
- [official_source](https://docs.cloud.google.com/managed-spark/docs/guides/use-dataproc-mcp)

## Setup

Use the interactive setup panel on [the detail page](https://www.mcpfolio.com/servers/google-cloud-managed-service-for-apache-spark) to view instructions for each supported client.