All integrations
GCP BigQuery
Databases
Run SQL against your warehouse from an agent step — with schema inspection first, so queries are written against what's actually there.
What teams build with this
Answer analytical questions without a dedicated reporting cycle
Join business data with system-of-record context for a report
Inspect table schemas before generating a query
What this integration is allowed to do
5 read-only
Reads data. Cannot change anything in the connected system.
Attach only the tools an agent needs. Run the whole integration against a vendor sandbox or the Fruxon simulator before it touches production.
Available tools
Each tool is attached per agent step, so an agent only gets what its job requires.
run_query | Execute a GoogleSQL query, returning results or a job reference if async | Read-only |
get_query_results | Fetch results from a completed or running job, or paginate large result sets | Read-only |
list_datasets | List all datasets in the project with IDs, names, and locations | Read-only |
list_tables | List all tables in a dataset with IDs, types, and creation times | Read-only |
get_table | Get table metadata: schema, columns, types, row count, partitioning config | Read-only |
Connect GCP BigQuery to your agents
Set up credentials once at the tenant level, then attach the tools you need to any agent.
