Skip to main content
Back to the BigQuery MCP server

MCP Gateway · ChatGPT

BigQuery icon

Connect BigQuery to ChatGPT

Finance and sales operations teams need warehouse numbers for reports, often on a deadline. Through the Speakeasy MCP Gateway, ChatGPT can pull those figures with read-only SQL, check a dataset's metadata and browse its tables, so a request doesn't wait in the data team's queue. Every BigQuery tool call is inspected and logged against a named employee.

Category
Data & analytics
Tools
6
Authentication
OAuth
ChatGPT
Web, desktop and mobile

Behind the MCP Gateway

Run BigQuery MCP behind the MCP Gateway

One URL for every agent, sign-in through your IdP, RBAC down to the tool, and every BigQuery call inspected and logged.

Deploy on MCP Gateway

Before you start

What BigQuery needs first

A Google Cloud project administrator with IAM admin access does the BigQuery side of the setup.

  • You need a Google Account that can administer the project and create OAuth credentials.
  • Granting roles needs IAM admin access, such as Project IAM Admin.
  • Billing is optional for initial setup.
  • External apps in Testing allow at most 100 test users, and authorizations expire after seven days.

In BigQuery

  1. Enable the BigQuery API in the project.
  2. Grant each user MCP Tool User, BigQuery Job User, and BigQuery Data Viewer.
  3. Configure the OAuth consent screen as Internal or External.
  4. For External apps, add the BigQuery scope and test users, or publish the app.
  5. Create an OAuth client and copy its credentials.
Full BigQuery setup guide in the docs

Set up

Add BigQuery to ChatGPT in 4 steps

  1. 01

    Add BigQuery from the catalog

    An admin finds BigQuery in the MCP Catalog (MCP Gateway > MCP > Catalog) and clicks Add. Speakeasy registers the vendor's server as a remote MCP server and proxies sessions to it. Nothing is copied or re-hosted.

    BigQuery uses OAuth. Servers that support dynamic client registration get their OAuth configuration applied automatically.

    Where MCP-scoped policies are enabled, the install offers a recommended risk policy for the new server that detects secrets and PII and inspects tool requests and responses.

  2. 02

    Choose who can use BigQuery

    Give teams the mcp:connect scope on the BigQuery server through team access or a role. ChatGPT connects to the BigQuery server's own URL, and the server's authorization decides who can connect and which tools they can call.

  3. 03

    Connect ChatGPT

    Import the organization's plugin marketplace into the ChatGPT workspace and set who gets each plugin.

    New MCP servers join the project's default plugin automatically. Each server's overview page shows which plugin it is published to, with Publish or Update to change it.

    Give the importing workspace admin collaborator access to the marketplace repository, and connect their GitHub account in ChatGPT under Plugins > GitHub > Manage.

    In ChatGPT, open Admin > Plugins > Add > Import marketplace.

    Set each plugin's installation policy, Installed or Available, per role.

    Enable the MCP servers the plugin connects to.

  4. 04

    Sign in and use BigQuery from ChatGPT

    The first time ChatGPT connects, it opens a browser so the person can sign in to Speakeasy through your identity provider.

    BigQuery needs its own OAuth grant, so each person connects it once. Until they do, BigQuery calls fail while the rest of the gateway keeps working.

    From then on, BigQuery's tools appear in ChatGPT, limited to what the person's access allows, and every call lands in the gateway's tool logs.

The marketplace syncs from GitHub once a day. Use Sync now to pick up a change straight away.

Use cases

What ChatGPT users do with BigQuery

Pull figures for the monthly report

Ask ChatGPT for revenue by region for the quarter, and it runs a read-only query and turns the result into a table for your report.

execute_sql_readonly

Check what a dataset is for

Before using a dataset in a board deck, read its metadata in ChatGPT to see what it holds and whether it fits your question.

get_dataset_infolist_table_ids

Confirm a metric's source table

When two reports disagree, ChatGPT shows the columns of each source table so you can tell whether they measure the same thing.

get_table_info

Tools

6 tools

Each BigQuery tool can be allowed or denied per team and role at the MCP Gateway before ChatGPT sees it.

list_dataset_ids

List BigQuery dataset IDs in a Google Cloud project.

get_dataset_info

Get metadata information about a BigQuery dataset.

list_table_ids

List table ids in a BigQuery dataset.

get_table_info

Get metadata information about a BigQuery table.

execute_sql_readonly

Run a read-only SQL query in the project and return the result. Prefer this tool over execute_sql if possible.

execute_sql

Run a SQL query in the project and return the result. Prefer the execute_sql_readonly tool if possible.

Control

What Speakeasy can see and stop in ChatGPT

The gateway covers every client the same way. The rest depends on what ChatGPT exposes to Speakeasy.

Tool logs

Gateway

Every BigQuery call is logged with the person and the client that made it.

Access by role

Gateway

People reach only the BigQuery tools their team or role allows.

Request and response blocking

Gateway

A risk policy scoped to BigQuery can reject a tool request before it reaches the server, or withhold a result from ChatGPT. MCP-scoped policies are enabled per organization.

Conversation import

ChatGPT

ChatGPT activity can be imported through OpenAI's Compliance API for review after the fact. It can't block in real time.

  • The workspace import needs a ChatGPT Business, Enterprise or Edu admin.

Questions

Frequently asked questions

Can ChatGPT block a BigQuery query before it runs?
No. ChatGPT activity can be imported through OpenAI's Compliance API for review after the fact, but it can't block in real time. Limit what each role can call at the gateway instead.
What does a Google Cloud admin set up for BigQuery?
They enable the BigQuery API, grant each user MCP Tool User, BigQuery Job User and BigQuery Data Viewer, configure the OAuth consent screen, and create an OAuth client.
How do ChatGPT users get BigQuery?
An admin adds BigQuery from the Speakeasy MCP Catalog and grants access by team or role. Import the organization's plugin marketplace into the ChatGPT workspace and set who gets each plugin. Each person then sees only the BigQuery tools their access allows.
Are BigQuery calls from ChatGPT logged?
Yes. BigQuery calls go through the MCP Gateway, which logs each tool call and attributes it to the person and the client that made it.

Connect more

BigQuery in other clients

AI everywhere.

Control here.