Google BigQuery for AI agents

Google BigQuery is a managed data warehouse for running fast SQL queries and machine learning over large datasets. Teams use it to query and update this data without standing up separate infrastructure. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Google BigQuery See the 63 actions ↓

Databases and spreadsheetsOAuth 2.0MCP + RESTcloud.google.com

AUDIT LOG · GOOGLE BIGQUERYPOLICY: acme-support

09:41:07 · claude · u_8f2read

google_bigquery.list_jobs

List BigQuery Jobs✓ allowed · 212ms

09:41:08 · claude · u_8f2read

google_bigquery.get_job

Get BigQuery Job✓ allowed · 164ms

09:41:09 · claude · u_8f2write

google_bigquery.create_table

Create BigQuery Table✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

google_bigquery.delete_model

Delete BigQuery ML Model✕ blocked · policy: deny

EVERY GOOGLE BIGQUERY CALL, ON THE RECORD

01 · USE CASES

What agents do in Google BigQuery.

Run a read-only SQL query

Run a SELECT query against a dataset to answer a question about recent order volume.

Check a table's schema

Look up a table's schema before writing a query that joins it with another dataset.

Approve a table delete

Delete an unused table only after an engineer confirms it is not referenced by any pipeline.

02 · ACTIONS

63 Google BigQuery actions, graded by risk.

Every Google BigQuery action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

google_bigquery.get_job
Get BigQuery Job
google_bigquery.list_jobs
List BigQuery Jobs
google_bigquery.get_dataset
Get BigQuery Dataset Metadata
google_bigquery.get_routine
Get BigQuery Routine
google_bigquery.list_models
List BigQuery Models
google_bigquery.list_tables
List BigQuery Tables
google_bigquery.list_datasets
List BigQuery Datasets
google_bigquery.list_projects
List BigQuery Projects
google_bigquery.list_routines
List BigQuery Routines
google_bigquery.list_locations
List BigQuery Data Transfer Locations
google_bigquery.list_table_data
List BigQuery Table Data
google_bigquery.get_table_schema
Get BigQuery Table Schema
google_bigquery.get_query_results
Get BigQuery Query Results
google_bigquery.list_reservations
List BigQuery Reservations
google_bigquery.get_bigquery_model
Get BigQuery ML Model
google_bigquery.get_service_account
Get BigQuery Service Account

+ 17 MORE

write

Create and change things. Allow, or ask the user first.

google_bigquery.create_table
Create BigQuery Table
google_bigquery.update_table
Update BigQuery Table
google_bigquery.create_dataset
Create BigQuery Dataset
google_bigquery.create_listing
Create Analytics Hub Listing
google_bigquery.create_routine
Create BigQuery Routine
google_bigquery.update_dataset
Update BigQuery Dataset
google_bigquery.update_routine
Update BigQuery Routine
google_bigquery.create_connection
Create BigQuery Connection
google_bigquery.update_connection
Update BigQuery Connection
google_bigquery.create_reservation
Create BigQuery Reservation
google_bigquery.create_data_exchange
Create Analytics Hub Data Exchange
google_bigquery.create_query_template
Create Analytics Hub Query Template
google_bigquery.create_capacity_commitment
Create Capacity Commitment
google_bigquery.create_dataexchanges_listings
Create Analytics Hub Listing
google_bigquery.create_locations_datapolicies
Create BigQuery Data Policy (v2beta1)
google_bigquery.create_reservation_assignment
Create BigQuery Reservation Assignment

+ 8 MORE

destructive

Delete, cancel or archive. Ask first, or deny outright.

google_bigquery.cancel_job
Cancel BigQuery Job
google_bigquery.delete_model
Delete BigQuery ML Model
google_bigquery.delete_table
Delete BigQuery Table
google_bigquery.delete_dataset
Delete BigQuery Dataset
google_bigquery.delete_routine
Delete BigQuery Routine
google_bigquery.delete_job_metadata
Delete BigQuery Job Metadata

03 · HOW IT WORKS

Google BigQuery in three steps.

01Your users connect Google BigQueryThey sign in to Google BigQuery on Arc0 Connect, under your brand, and approve the access you ask for.
02You set the rulesReads run, writes like “create BigQuery Table” can wait for the user, and “delete BigQuery ML Model” can be denied outright.
03Any agent can actYour agent calls Google BigQuery through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('google_bigquery', {
  read: 'allow',
  write: 'ask',        // create_table
  destructive: 'deny',  // delete_model
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Google BigQuery connects.

Users sign in to Google BigQuery on Arc0 Connect and approve the scopes you request. Build with Arc0’s Google BigQuery OAuth app, or bring your own so the Google BigQuery consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Google BigQuery connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: OAuth 2.0 · Service account
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Google BigQuery from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More databases and spreadsheets apps.

Google Sheets58 actions

ALL DATABASES AND SPREADSHEETS APPS →

07 · FAQ

Google BigQuery and Arc0, answered.

Q01

Can I use Google BigQuery with Claude, ChatGPT or Cursor?

Yes. Connect Google BigQuery to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Google BigQuery actions you allow.

Q02

How do users connect Google BigQuery?

Q03

Which Google BigQuery actions can my agent take?

63 in total: 33 read, 24 write and 6 destructive, such as “create BigQuery Table”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Google BigQuery?

Yes. Actions like “delete BigQuery ML Model” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Google BigQuery too?

Yes. The same Google BigQuery connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Google BigQuery into your agent.

Your users connect Google BigQuery once, under your brand. Your agent gets 63 actions behind your policies, with every call on the record.

Connect Google BigQuery Browse all apps →

Free to build · MCP + REST · Audit log on every plan