Google Cloud's managed remote MCP server for BigQuery (GA) lets agents list datasets and tables, inspect metadata and run SQL. It uses OAuth 2.0 with IAM and requires the MCP Tool User role plus BigQuery permissions. It is one of several Google-managed MCP endpoints, alongside GKE, Compute Engine, Cloud Run, Cloud Logging and more.
Also available as
Connect
- 1Connect it in ChatGPT
Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://bigquery.googleapis.com/mcp as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.
- 2Or add it to Codex or the API
codex mcp add google-bigquery --url https://bigquery.googleapis.com/mcp codex mcp login google-bigqueryThe login command opens a browser to finish OAuth.
Configs are generated from the publisher's documented endpoint. Check their docs for plan requirements and scopes. New to this? Read the step-by-step tutorial.
Tools 6
list_dataset_idsget_dataset_infolist_table_idsget_table_infoexecute_sqlexecute_sql_readonlyThings to ask
- “List the datasets in my analytics project”
- “Describe the schema of the events table”
- “What were daily active users over the last 7 days?”
- “Run a read-only query for the top 10 products by revenue”