Skip to main content
Glama
warrenzhu25

Dataproc MCP Server

by warrenzhu25
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATAPROC_MCP_TRANSPORTNoCustom transport method for the MCP server
GOOGLE_APPLICATION_CREDENTIALSNoPath to service account JSON file for Google Cloud authentication

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
list_clustersB

List Dataproc clusters in a project and region.

Args:
    project_id: Google Cloud project ID (optional, uses gcloud config default)
    region: Dataproc region (optional, uses gcloud config default)
create_clusterB

Create a new Dataproc cluster.

Args:
    cluster_name: Name for the new cluster
    project_id: Google Cloud project ID (optional, uses gcloud config default)
    region: Dataproc region (optional, uses gcloud config default)
    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
delete_clusterB

Delete a Dataproc cluster.

Args:
    cluster_name: Name of the cluster to delete
    project_id: Google Cloud project ID (optional, uses gcloud config default)
    region: Dataproc region (optional, uses gcloud config default)
get_clusterA

Get details of a specific Dataproc cluster.

Args:
    cluster_name: Name of the cluster
    project_id: Google Cloud project ID (optional, uses gcloud config default)
    region: Dataproc region (optional, uses gcloud config default)
submit_jobB

Submit a job to a Dataproc cluster.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    cluster_name: Target cluster name
    job_type: Type of job (spark, pyspark, spark_sql, hive, pig, hadoop)
    main_file: Main file/class for the job
    args: Job arguments
    jar_files: JAR files to include
    properties: Job properties
list_jobsC

List jobs in a Dataproc cluster.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    cluster_name: Cluster name (optional)
    job_states: Filter by job states
get_jobC

Get details of a specific job.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    job_id: Job ID
cancel_jobA

Cancel a running job.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    job_id: Job ID to cancel
create_batch_jobB

Create a Dataproc batch job.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    batch_id: Unique identifier for the batch job
    job_type: Type of batch job (spark, pyspark, spark_sql)
    main_file: Main file/class for the job
    args: Job arguments
    jar_files: JAR files to include
    properties: Job properties
    service_account: Service account email
    network_uri: Network URI
    subnetwork_uri: Subnetwork URI
list_batch_jobsC

List Dataproc batch jobs.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    page_size: Number of results per page
get_batch_jobB

Get details of a specific batch job.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    batch_id: Batch job ID
delete_batch_jobC

Delete a batch job.

Args:
    project_id: Google Cloud project ID
    region: Dataproc region
    batch_id: Batch job ID to delete
compare_batch_jobsA

Compare two Dataproc batch jobs and return detailed differences.

Args:
    batch_id_1: First batch job ID to compare
    batch_id_2: Second batch job ID to compare
    project_id: Google Cloud project ID (optional, uses gcloud config default)
    region: Dataproc region (optional, uses gcloud config default)

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
get_clusters_resourceGet list of all Dataproc clusters.
get_jobs_resourceGet list of all Dataproc jobs.
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored across 13 tools

Disambiguation4/5

Most tools have clear distinct purposes targeting specific Dataproc resources (clusters, batch jobs, regular jobs). However, there is some potential overlap between 'cancel_job' and 'delete_batch_job' as both involve termination operations, and 'submit_job' vs 'create_batch_job' might cause confusion about when to use each, though descriptions clarify batch vs cluster job contexts.

Naming Consistency5/5

Excellent consistency with a clear verb_noun pattern throughout (e.g., create_cluster, list_batch_jobs, get_job). All tools use snake_case with descriptive verbs (create, delete, get, list, submit, cancel, compare), making them predictable and easy to understand.

Tool Count5/5

13 tools is well-scoped for a Dataproc server covering clusters, batch jobs, and regular jobs. Each tool earns its place by providing essential operations (CRUD, listing, comparison) without unnecessary redundancy, fitting the domain's complexity appropriately.

Completeness4/5

The toolset provides strong coverage for Dataproc operations, including CRUD for clusters and batch jobs, job management, and listing. Minor gaps include no update operations for clusters or batch jobs (e.g., update_cluster, update_batch_job) and no tool for stopping or pausing clusters, but core workflows are well-supported.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources