create_cluster

Set up a new Dataproc cluster by specifying project ID, region, cluster name, worker instances, machine type, disk size, and image version. Streamline big data processing on Google Cloud.

Instructions

Create a new Dataproc cluster.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    cluster_name: Name for the new cluster
    num_instances: Number of worker instances
    machine_type: Machine type for cluster nodes
    disk_size_gb: Boot disk size in GB
    image_version: Dataproc image version

Input Schema

Name	Required	Default
`cluster_name`	Yes
`disk_size_gb`	No
`image_version`	No	2.1-debian11
`machine_type`	No	n1-standard-4
`num_instances`	No
`project_id`	Yes
`region`	Yes

Input Schema (JSON Schema)

{
  "properties": {
    "cluster_name": {
      "title": "Cluster Name",
      "type": "string"
    },
    "disk_size_gb": {
      "default": 100,
      "title": "Disk Size Gb",
      "type": "integer"
    },
    "image_version": {
      "default": "2.1-debian11",
      "title": "Image Version",
      "type": "string"
    },
    "machine_type": {
      "default": "n1-standard-4",
      "title": "Machine Type",
      "type": "string"
    },
    "num_instances": {
      "default": 2,
      "title": "Num Instances",
      "type": "integer"
    },
    "project_id": {
      "title": "Project Id",
      "type": "string"
    },
    "region": {
      "title": "Region",
      "type": "string"
    }
  },
  "required": [
    "project_id",
    "region",
    "cluster_name"
  ],
  "title": "create_clusterArguments",
  "type": "object"
}

Dataproc MCP Server

create_cluster

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Dataproc MCP Server

Related Tools

MCP directory API