Connect Google BigQuery to Your AI Agent

Identify the project and tables, inspect their fields, and ask for a query focused on your business question.

Try a Google BigQuery Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Google BigQuery

Inspect a Dataset Before Querying

Read tables and their schemas to understand the available data.

/oo Google BigQuery: List tables in BigQuery project [project ID], dataset [dataset ID]. Read schemas for [table IDs] and explain which fields can answer [question].

Answer a Data Question with SQL

Execute a read-only SQL query and summarize completed results.

/oo Google BigQuery: In BigQuery project [project ID], region [region], inspect [dataset.table] and run a SELECT query to answer [question] for [date range]. Check for completion and summarize the results without changing data.

Start Working with Google BigQuery

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Google BigQuery

Authorize your Google account for BigQuery.
Connect Google BigQuery →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

A Google account with the required BigQuery project and resource permissions.
Supply the project and job region. Query execution may incur BigQuery usage charges; Cloud Storage transfers require relevant storage access.

Google BigQuery Tools

BigQuery operations cover projects, datasets, tables and rows, SQL jobs, Cloud Storage imports and exports, routines, and model metadata.

Schemas and Table Data

Browse projects, datasets, tables, and rows for analysis.

SQL and Data Transfer Jobs

Run SQL, check jobs, and start Cloud Storage load or export jobs.

Dataset and Table Management

Create, revise, or delete datasets and tables, and insert rows with per-row error reporting.

32 tools

List Projects

List Google Cloud projects accessible to BigQuery.

google_bigquery.list_projects

List Datasets

List BigQuery datasets in a Google Cloud project.

google_bigquery.list_datasets

Get Dataset

Retrieve BigQuery dataset metadata.

google_bigquery.get_dataset

List Tables

List BigQuery tables in a dataset.

google_bigquery.list_tables

Get Table

Retrieve BigQuery table metadata, including schema when available.

google_bigquery.get_table

List Table Data

List rows from a BigQuery table.

google_bigquery.list_table_data

Query

Run a BigQuery SQL query and return the first page of results.

google_bigquery.query

Get Query Results

Poll a BigQuery query job and return a page of results.

google_bigquery.get_query_results

Get Job

Retrieve BigQuery job metadata.

google_bigquery.get_job

List Jobs

List BigQuery jobs in a Google Cloud project.

google_bigquery.list_jobs

Cancel Job

Cancel a BigQuery job.

google_bigquery.cancel_job

Start Query Job

Start an asynchronous BigQuery query job.

google_bigquery.start_query_job

Start Load Job From Gcs

Start an asynchronous BigQuery load job from Cloud Storage objects.

google_bigquery.start_load_job_from_gcs

Start Extract Job To Gcs

Start an asynchronous BigQuery extract job to Cloud Storage objects.

google_bigquery.start_extract_job_to_gcs

Create Dataset

Create a BigQuery dataset.

google_bigquery.create_dataset

Patch Dataset

Patch BigQuery dataset metadata.

google_bigquery.patch_dataset

Update Dataset

Replace BigQuery dataset metadata with the supplied dataset resource fields.

google_bigquery.update_dataset

Delete Dataset

Delete a BigQuery dataset, optionally deleting contained tables when explicitly requested.

google_bigquery.delete_dataset

Create Table

Create a BigQuery table.

google_bigquery.create_table

Patch Table

Patch BigQuery table metadata.

google_bigquery.patch_table

Update Table

Replace BigQuery table metadata with the supplied table resource fields.

google_bigquery.update_table

Delete Table

Delete a BigQuery table from a dataset.

google_bigquery.delete_table

Insert All

Insert a small batch of rows into a BigQuery table.

google_bigquery.insert_all

List Routines

List BigQuery routines in a dataset.

google_bigquery.list_routines

Get Routine

Retrieve BigQuery routine metadata.

google_bigquery.get_routine

Create Routine

Create a BigQuery routine such as a user-defined function or stored procedure.

google_bigquery.create_routine

Update Routine

Replace BigQuery routine metadata and definition fields.

google_bigquery.update_routine

Delete Routine

Delete a BigQuery routine from a dataset.

google_bigquery.delete_routine

List Models

List BigQuery ML models in a dataset.

google_bigquery.list_models

Get Model

Retrieve BigQuery ML model metadata.

google_bigquery.get_model

Patch Model

Patch BigQuery ML model metadata such as friendly name, description, or labels.

google_bigquery.patch_model

Delete Model

Delete a BigQuery ML model from a dataset.

google_bigquery.delete_model

Frequently Asked Questions

What information does a query need?

Provide the project, table references, question or SQL, and job region. The connected account must be allowed to run jobs and access the referenced data.

Can I validate SQL before running it?

Yes. Request a dry run to validate the query without executing it, then decide whether to run it using the reported information.

Does a query always return all rows immediately?

No. It may still be running or return only part of the result. Use the job reference to check completion and retrieve remaining result pages when needed.