Datasets, tables and GoogleSQL queries with a cost limit. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Google BigQuery form, the endpoint selector, and this connector’s actual tool preview. The form and preview have not been saved. Select a screenshot to open it at full size.
1. Create a connection and enter the settings
In GateRook, open Connections, select Add connection, search for Google BigQuery, choose its card and select Continue to configure.
Identify the Google Cloud project that will run and pay for queries, and the datasets you want the AI to use. Queries can incur BigQuery charges.
Prepare local Application Default Credentials or a service account key. A read-only setup generally needs BigQuery Data Viewer on the datasets and BigQuery Job User on the query project.
Enter a Name, for example bigquery-demo. Your AI app uses this name to choose the connection.
Enter Project and the datasets in Datasets, using dataset or project.dataset. Set Location to the location of the data, such as EU, when needed.
Choose Existing Google sign-in (ADC) or Service account key (JSON) under Authentication. Optionally set Service account to impersonate for a dedicated query identity.
Open Advanced and set Data per statement to an appropriate limit. GateRook checks read queries with a dry run before executing them.
Choose Development, Staging or Production to match the service. Review the connector’s limit and access settings before continuing.
2. Test the connection and add it to an endpoint
Select Continue to test. GateRook checks the settings from your computer. Review the result and resolve any connection, certificate or permission error before continuing.
For permission errors, check both dataset access and permission to create jobs in Project. A location mismatch or the configured data limit can reject a query even when authentication succeeds.
After the test passes, select Continue to add to an endpoint. Choose the endpoint your AI app uses, review its tool modes, then select Save connection. GateRook offers default as the starter endpoint.
3. Use the connection from your AI IDE
After saving Google BigQuery on the endpoint and passing its connection test, ask your AI app to use bigquery-demo, or the name you chose. If its tools are missing, confirm the endpoint assignment and refresh the MCP connection or start a new chat.
The preview below shows this connector’s default tools before saving. The table explains what each tool can do; connection settings, credentials and endpoint policies can restrict access further.
Start with a small read request. Replace example resource names with existing resources your connection may access. Open Activity after the call to inspect its connection, tool, arguments, policy decision and result metadata.
Ask your AI, for example
- “List the datasets available through bigquery-demo.”
- “Describe the partitioning and columns of analytics.orders on bigquery-demo.”
- “Using bigquery-demo, count orders by status for yesterday, respecting the configured data limit.”
| Tool | What it does | Starts as |
|---|---|---|
bigquery_list_datasets | Datasets agents may use in the connection's project. | Read only |
bigquery_list_tables | Tables, views and their kinds in one dataset. | Read only |
bigquery_describe_table | Columns with nested fields, partitioning, clustering, row count, size and a view's query. | Read only |
bigquery_query | One SELECT, checked by a free dry run before it runs: BigQuery must call it a SELECT of allowed tables within the connection's byte limit. Pages with nextCursor. | Read only |
bigquery_execute | One DML or DDL statement. You approve the exact text with the bytes it processes. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.