# Google BigQuery
ID: 06-google-bigquery
Page: https://gtmmcps.com/tools/06-google-bigquery
JSON: https://gtmmcps.com/data/tools/06-google-bigquery.json
Documentation references: https://gtmmcps.com/docs/06-google-bigquery/
Category: RevOps Infra
MCP support: official
Testing: RESEARCHED
API access: free
Last checked: 2026-09-07
Endpoint check: not-probed; date: Not recorded

Google Cloud's serverless data warehouse, where many RevOps teams land CRM, product and billing data for modelling and reporting; a first-party remote MCP server exposes dataset and table metadata and SQL execution to agents.

## MCP links
- https://bigquery.googleapis.com/mcp
- https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp

## Sources
- https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp
- https://docs.cloud.google.com/free/docs/free-cloud-features
- https://cloud.google.com/bigquery/pricing
- https://bigquery.googleapis.com/mcp

## Research notes
Verified 2026-09-07: POST of an MCP initialize to https://bigquery.googleapis.com/mcp with no token returned HTTP 200 with a JSON-RPC result, serverInfo name "StatelessServer" version "ESF" (protocolVersion 2025-03-26); the control POST to /zzz-not-a-route returned 404. Initialize is open and IAM is enforced per tool call. Google's cloud documentation moved from cloud.google.com to docs.cloud.google.com with 301 redirects on this date; the entry records the destination URLs. Snowflake, the other warehouse in this file, is the natural comparison: both now ship a first-party MCP, and BigQuery's is reachable on a free-tier project with no contract. 2026-09-07: https://bigquery.googleapis.com/mcp returned 200 with a JSON-RPC initialize result to an MCP initialize POST (https://bigquery.googleapis.com/mcp).

## Named capabilities
Tool names below are reported by sources. Their presence is not a successful call.
- cancel_job: Cancel a running BigQuery job.  Use this tool to cancel a query job that is currently executing (i.e. returned `job_complete: false` with a `job_id` from `execute_sql` or `execute_sql_readonly`). Specify the `job_id` to abort.; evidence: live-list; party: 
- execute_sql: Run a SQL query in the project and return the result. Prefer the `execute_sql_readonly` tool if possible.  This tool can execute any query that bigquery supports including:  * SQL Queries (`SELECT`, `INSERT`, `UPDATE`, `DELETE`, `CREATE`, e; evidence: live-list; party: 
- execute_sql_readonly: Run a read-only SQL query in the project and return the result. Prefer this tool over `execute_sql` if possible.  This tool is restricted to only `SELECT` statements. `INSERT`, `UPDATE`, and `DELETE` statements and stored procedures aren't; evidence: live-list; party: 
- get_dataset_info: Get metadata information about a BigQuery dataset or BigLake namespace.; evidence: live-list; party: 
- get_job: Get information and status about a BigQuery job.  Use this tool to check the status, statistics, or configuration of a job using its `job_id`.; evidence: live-list; party: 
- get_query_results: Get the results of a BigQuery SQL query job.  Use this tool ONLY when: 1. A previous `execute_sql` or `execute_sql_readonly` call returned `job_complete: false` with a `job_id`    (poll with this tool until `job_complete: true`), OR 2. You; evidence: live-list; party: 
- get_table_info: Get metadata information about a BigQuery table or BigLake table.; evidence: live-list; party: 
- list_dataset_ids: List BigQuery dataset IDs and BigLake namespaces in a Google Cloud project. Supports pagination. Use `page_size` to limit results and `page_token` to retrieve next page.; evidence: live-list; party: 
- list_table_ids: List table ids in a BigQuery dataset or BigLake namespace. Supports pagination. Use `page_size` to limit results and `page_token` to retrieve next page.; evidence: live-list; party: 

## CLI evidence
Status: none-found

Read current vendor documentation before configuring or running commands.