Google BigQuery
Google BigQuery connector for executing SQL queries, managing datasets and tables, streaming data inserts, and monitoring jobs through the BigQuery REST API v2.
What you can ask
- Run a query to count signups by source over the last 30 days from the
analytics.eventstable. - List the largest tables in the
proddataset by row count. - Show me query jobs from the last 24 hours that scanned more than 1TB.
Set up
Google BigQuery needs an OAuth application from your organization before anyone can connect. An organization admin completes these steps once.
- Go to Organization > Connectors and find Google BigQuery. Click Enable, and choose which tools to allow.
- Create a Google Cloud project.
- Turn on the BigQuery API.
- Configure the OAuth consent screen.
- Create credentials, choose OAuth client ID, and set the type to Web application.
- Add the exact Redirect URI shown in the connector settings.
- Copy the client ID and client secret into the connector, then save it.
- Each member connects their own account the first time they use it.
⚠️ Warning: Do not enter your Devs.ai or Google BigQuery login email or password in the OAuth application fields.
To use one account for the whole organization, turn on Share one connection with everyone. Every member's agents then act as that account, with exactly the access it has.
OAuth scopes used by these tools (3)
Grant the scopes for the tools you plan to allow.
https://www.googleapis.com/auth/bigqueryhttps://www.googleapis.com/auth/bigquery.insertdatahttps://www.googleapis.com/auth/bigquery.readonly
Tools
Google BigQuery offers 22 tools. Admins choose which ones agents can use. See Tool permission groups.
Read (12)
View and search information without changing it.
| Tool | What it does |
|---|---|
describe_query | Preflight a SQL query without running it: dry-runs it in BigQuery and returns the base tables it reads (a view appears as its underlying tables), its statement type and a reference_status. |
export_table_to_gcs | Export a BigQuery table to Google Cloud Storage in CSV, JSON, Avro, or Parquet format. |
get_dataset | Get detailed information about a specific BigQuery dataset including description, location, labels, and access controls. |
get_job | Get detailed information about a specific BigQuery job including status, configuration, and statistics. |
get_query_results | Get results from a previously executed query using its job ID. |
get_table | Get detailed information about a BigQuery table including schema, row count, size, and partitioning config. |
list_datasets | List datasets in a BigQuery project. |
list_jobs | List BigQuery jobs in a project. |
list_projects | List all BigQuery projects accessible to the authenticated user. |
list_table_data | Read rows from a BigQuery table. |
list_tables | List tables in a BigQuery dataset. |
validate_credential | Validate Google BigQuery credentials. |
Write (3)
Create or send data.
| Tool | What it does |
|---|---|
create_dataset | Create a new dataset in a BigQuery project. |
create_table | Create a new table in a BigQuery dataset with a typed schema. |
insert_table_data | Stream-insert rows into a BigQuery table. |
Delete or overwrite (7)
Remove or replace existing data.
| Tool | What it does |
|---|---|
cancel_job | Cancel a running BigQuery job. |
copy_table | Copy a BigQuery table to a new location (within/across datasets or projects). |
delete_dataset | Delete a BigQuery dataset. |
delete_table | Delete a BigQuery table permanently. |
run_query | Execute a SQL query in BigQuery and return results. |
update_dataset | Update a BigQuery dataset's description, friendly name, labels, or default table expiration. |
update_table | Update a BigQuery table's description, friendly name, labels, or schema (add new columns only — cannot remove/rename). |