The request names Google Cloud Dataproc, which is not itself among the candidates. The closest in the list is Google Dataproc Metastore 3, a managed Hive metastore on Google Cloud that exposes an API, though it does not run Dataproc clusters or jobs. Dataproc's own skills 1 (dataproc-skills) interact with Dataproc clusters and jobs.
A question back: Do you need to manage Dataproc clusters and jobs themselves, or only the Hive metastore they use?
- 1
- 2
Dataproc Metastore APIgoogle.comverified and signed
Google's Dataproc Metastore is a fully managed Apache Hive metastore on Google Cloud, offering an API with actions such as services.list and services.queryMetadata 12.
official:API · Dataproc Metastore API
for agents: metastore.projects.locations.services.queryMetadata · metastore.projects.locations.get · metastore.projects.locations.services.list
- 3
Databricksdatabricks.comverified and signed
Databricks is a unified data and AI platform for ETL, warehousing and Spark-based data engineering jobs, reachable through its CLI and SDK 13.
official:SDK · databricks-cliskill · databricks-coreskill · databricks-appsskill · databricks-pipelines+71 community tools built for it
for agents: databricks-model-serving · databricks-jobs · databricks
Sources
- 1Cline - AI Coding, Open Source and Open Choicecline.bot · read 2026-10-30
- 3Dataproc Metastore documentation | Google Cloud Documentationdocs.cloud.google.com · read 2026-10-29
- 4Databricks: Leading Data and AI Platform for Enterprisesdatabricks.com · read 2026-10-29
- 10dataproc-skills: declares "dataproc-skills" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12Dataproc Metastore API: declares "metastore.projects.locations.services.queryMetadata" (the record we read and signed)unfragile.ai · read 2026-10-24
- 13databricks-model-serving: declares "databricks-model-serving" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
dataproc-skills · dataproc-skills verified and signed
Skills to interact with your Dataproc clusters and jobs.
delta.io · delta-spark verified and signed
metastore.projects.locations.services.queryMetadata · Dataproc Metastore API verified and signed
Query DPMS metadata.
google api · @google-cloud/dataproc verified and signed
cloudbuild.projects.workerPools.patch · Cloud Build API verified and signed
Updates a `WorkerPool`.
databricks-model-serving · databricks-model-serving verified and signed
Databricks Model Serving endpoint lifecycle and ops. Use when asked to: CRUD serving endpoints (CLI or MLflow Deployments client); configure traffic routing for A/B / canary deploys and zero-downtime version swaps; retrieve OpenAPI schemas; inspect logs, metrics, or permissions; manage legacy AI Gat
looker.projects.locations.operations.list · Looker (Google Cloud core) API verified and signed
Lists operations that match the specified filter in the request.
monitoring.projects.timeSeries.query · Cloud Monitoring API verified and signed
Queries time series by using Monitoring Query Language (MQL).
dataframe · polars-runtime-32 verified and signed
bigquery.routines.insert · BigQuery API verified and signed
Creates a new routine in the dataset.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.