Google BigQuery MCP integration for AI agents.
Connect AI agents to Google BigQuery through 32 structured actions, including get dataset, create dataset, cancel job, and insert all. Review authentication…
- ACTION CONTRACTS
- 32
- AUTHENTICATION
- OAuth 2.0
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Google BigQuery integration exposes
The Google BigQuery Agent App exposes 32 provider-backed actions for data and developer tools work. Its current contract lets an authorized agent retrieve bigquery dataset metadata, create a bigquery dataset, and cancel a bigquery job. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses OAuth 2.0. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Google BigQuery account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Google BigQuery capabilities.
Showing 12 of 32 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_datasetREADRetrieve BigQuery dataset metadata.
INPUTS: projectId / datasetId / selectedFields
create_datasetWRITECreate a BigQuery dataset.
INPUTS: projectId / datasetId / location / friendlyName / description
cancel_jobHIGH IMPACTCancel a BigQuery job.
INPUTS: projectId / jobId / location
insert_allREVIEWInsert a small batch of rows into a BigQuery table.
INPUTS: projectId / datasetId / tableId / rows / skipInvalidRows
create_routineWRITECreate a BigQuery routine.
INPUTS: projectId / datasetId / routineId / routineType / language
create_tableWRITECreate a BigQuery table.
INPUTS: projectId / datasetId / tableId / schema / friendlyName
delete_datasetHIGH IMPACTDelete a BigQuery dataset.
INPUTS: projectId / datasetId / deleteContents
delete_modelHIGH IMPACTDelete a BigQuery model.
INPUTS: projectId / datasetId / modelId
delete_routineHIGH IMPACTDelete a BigQuery routine.
INPUTS: projectId / datasetId / routineId
delete_tableHIGH IMPACTDelete a BigQuery table.
INPUTS: projectId / datasetId / tableId
get_jobREADRetrieve BigQuery job metadata.
INPUTS: projectId / jobId / location
get_modelREADRetrieve a BigQuery model.
INPUTS: projectId / datasetId / modelId
INPUT CONTRACTS
Know what the action needs before it runs.
get_dataset
projectIdREQUIRED- The Google Cloud project ID that owns the BigQuery resource.
datasetIdREQUIRED- The BigQuery dataset ID.
selectedFieldsOPTIONAL- A subset of fields to return, formatted as a comma-separated list.
create_dataset
projectIdREQUIRED- The Google Cloud project ID that owns the BigQuery resource.
datasetIdREQUIRED- The BigQuery dataset ID.
locationOPTIONAL- The BigQuery job location, such as US or europe-west1.
friendlyNameOPTIONALdescriptionOPTIONAL
cancel_job
projectIdREQUIRED- The Google Cloud project ID that owns the BigQuery resource.
jobIdREQUIRED- The BigQuery job ID.
locationOPTIONAL- The BigQuery job location, such as US or europe-west1.
insert_all
projectIdREQUIRED- The Google Cloud project ID that owns the BigQuery resource.
datasetIdREQUIRED- The BigQuery dataset ID.
tableIdREQUIRED- The BigQuery table ID.
rowsREQUIREDskipInvalidRowsOPTIONAL
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Dataset
Retrieve BigQuery dataset metadata. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_datasetControl Create Dataset
Create a BigQuery dataset. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_datasetVerify with Create Dataset
Create a BigQuery dataset. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
create_datasetSAFETY BOUNDARY
Operate Google BigQuery with explicit limits
- Authorize Google BigQuery with OAuth 2.0 and grant only the provider access required by the selected actions.
- 13 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `cancel_job`, `delete_dataset`, and `delete_model` as high-impact operations and require an explicit approval boundary.
- The sampled contract declares provider scopes including `https://www.googleapis.com/auth/bigquery`, `https://www.googleapis.com/auth/bigquery.readonly`, `https://www.googleapis.com/auth/bigquery.insertdata`, and `https://www.googleapis.com/auth/devstorage.read_write`; verify the complete action contract before execution.
- After a call, inspect the structured result and execution record before reporting that the Google BigQuery task completed successfully.
CONNECTION MODEL
OAuth 2.0
Google BigQuery uses OAuth 2.0. Connection requirements and availability are determined by the provider and the Working Machines deployment.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 15
- WRITE SIGNALS
- 8
- HIGH IMPACT
- 5
- REVIEW SIGNALS
- 4
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Google BigQuery.