What can AI agents do with Google BigQuery through Ferentin?

Ferentin exposes 6 Google BigQuery MCP tools to your AI agents, grouped as Discover (2 tools), Access (2 tools) and Manage (2 tools). Every call is checked against your Ferentin policies before it reaches Google BigQuery.

How does Ferentin secure Google BigQuery access?

Requests through the Google BigQuery integration are covered by OAuth 2.0 consent, cloud iam authorization, no API keys and audit logging. These controls are applied by Ferentin, not by Google BigQuery, so they hold across every connected agent.

What permissions does the Google BigQuery integration require?

The Google BigQuery integration requests 1 OAuth 2.0 scope: https://www.googleapis.com/auth/bigquery

How do I connect Google BigQuery to Ferentin?

Open the Ferentin admin console, add Google BigQuery as a new connection and authenticate with OAuth 2.0. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.

Is the Google BigQuery integration generally available?

The Google BigQuery integration is currently beta on Ferentin.

MCP Servers

Google BigQuery

Beta

Query and explore BigQuery data warehouses. Discover datasets/tables, inspect schema, and run read-only SQL — governed by Cloud IAM.

MCP ServersAnalyticsData WarehouseSQL

Configure Setup guide

How it works

Every agent request passes through Ferentin policy before it reaches Google BigQuery.

AI agentAsks for something
Ferentin policies
- OAuth 2.0 consent
- Cloud iam authorization
- No API keys
- Audit logging
Google BigQuery MCP serverAuthorized connection
Governed resultMasked, logged, returned

What you can do with Google BigQuery

Discover
Search and browse what exists, without opening the content itself.
2 tools
Access
Read content and metadata, subject to masking policy.
2 tools
Manage
Create, update, organise and remove items.
2 tools

Technical capabilities6 tools

Discover

list_dataset_ids
list_table_ids

Access

get_dataset_info
get_table_info

Manage

execute_sql_readonly
execute_sql

Overview

BigQuery is Google Cloud's serverless, petabyte-scale data warehouse for analytics over structured and semi-structured data using GoogleSQL.

Developer docs

Ferentin integration

Ferentin's Google BigQuery MCP server connects agents to a project's datasets through OAuth2 + Cloud IAM, with tools for dataset/table discovery, schema inspection, and read-only SQL execution. execute_sql is SELECT-only on the managed endpoint; access is scoped by the signing-in identity's IAM grants.

Connection details

Status: Beta
Integration type: Remote MCP server
Authentication: OAuth 2.0
Hosting: Vendor-hosted endpoint
Required scopes: 1
Data actions: Read and write
MCP tools: 6

Configure Setup guide

Permissions1 scope

https://www.googleapis.com/auth/bigquery

Security controls4

OAuth 2.0 consent
Cloud iam authorization
No API keys
Audit logging

Technical details

Vendor: Google BigQuery
Endpoint: bigquery.googleapis.com

Google does not support Dynamic Client Registration (DCR) — each tenant must create its own OAuth client in Google Cloud Console.
Authentication is OAuth 2.0 + Google Cloud IAM. API keys are not accepted; access is enforced by the signing-in identity's IAM roles.
Use access_type=offline to receive a refresh token for long-lived access.
On the fully-managed server, execute_sql accepts SELECT statements only.
Query results are limited to 3,000 rows and 3 minutes of processing time.
The scope https://www.googleapis.com/auth/bigquery is required; cloud-platform works as a superset.
Google Drive-backed external tables cannot be queried through this server.

Frequently asked about Google BigQuery

What can AI agents do with Google BigQuery through Ferentin?: Ferentin exposes 6 Google BigQuery MCP tools to your AI agents, grouped as Discover (2 tools), Access (2 tools) and Manage (2 tools). Every call is checked against your Ferentin policies before it reaches Google BigQuery.
How does Ferentin secure Google BigQuery access?: Requests through the Google BigQuery integration are covered by OAuth 2.0 consent, cloud iam authorization, no API keys and audit logging. These controls are applied by Ferentin, not by Google BigQuery, so they hold across every connected agent.
What permissions does the Google BigQuery integration require?: The Google BigQuery integration requests 1 OAuth 2.0 scope: https://www.googleapis.com/auth/bigquery
How do I connect Google BigQuery to Ferentin?: Open the Ferentin admin console, add Google BigQuery as a new connection and authenticate with OAuth 2.0. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.
Is the Google BigQuery integration generally available?: The Google BigQuery integration is currently beta on Ferentin.