Can AI agents automate Google BigQuery?

Google BigQuery is automatable today through the BigQuery REST API at https://bigquery.googleapis.com. REST v2 covers datasets, tables, tabledata, jobs including synchronous query, models, routines, and row-access policies. Callers authenticate with OAuth 2.0 bearer tokens. Workloads on Google Cloud use attached service-account credentials through Application Default Credentials. Official client libraries exist for C#, Go, Java, Node.js, PHP, Python, and Ruby. The official bq CLI, shipped with the Google Cloud CLI, runs non-interactive query, load, extract, and resource commands and accepts --format values such as prettyjson. Google hosts a first-party remote MCP server at https://bigquery.googleapis.com/mcp, enabled when the BigQuery API is enabled, using OAuth 2.0 and IAM. Tools list datasets and tables and execute SQL. execute_sql can write. Queries are capped at three minutes and 3,000 rows. Google Drive external tables are unsupported. Zapier, Make, and n8n publish BigQuery connectors. Microsoft lists a Power Automate Independent Publisher preview connector. HTTP webhooks for table changes were not established. Computer-use viability is unassessed. API and CLI both score 8; API is the best path because it is the machine contract and MCP remains narrower than REST.

Best path today: api · Overall automatability: 8/10