How to Connect Google BigQuery to ChatGPT via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Google BigQuery, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Google BigQuery + ChatGPT

Let your AI explore and query Google BigQuery: list projects, datasets and tables, read schemas, preview rows for free, estimate a query's cost with a dry run before running it, page through results and check the job history. Signs in with your Google account.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET

Step 1 — Get credentials

1. Open console.cloud.google.com, pick or create a project, then go to APIs & Services → Library and enable the BigQuery API.
2. Open APIs & Services → OAuth consent screen. Choose Internal if you are on Google Workspace (the simplest option), otherwise External. For External, set the publishing status to In production: while the app is in Testing, Google revokes its refresh tokens after 7 days and the connector stops working every week. For your own account you can click through the "unverified app" warning.
3. Open APIs & Services → Credentials → Create credentials → OAuth client ID, choose the application type Web application and add the authorized redirect URI https://cloud.anythingmcp.com/api/mcp-oauth/callback. If you host AnythingMCP yourself, enter https://your-anythingmcp-host/api/mcp-oauth/callback instead.
4. Paste the client ID into GOOGLE_CLIENT_ID and the client secret into GOOGLE_CLIENT_SECRET, then install the connector.
5. On the connector page, click Authorize with Provider and sign in with the Google account whose BigQuery data the AI should use. The refresh token is stored encrypted and access tokens are renewed automatically.

One Google client for all Google connectors: the same Cloud project and OAuth client can serve every Google connector, from Gmail and Google Sheets to Search Console and Firebase. Enable each API in that project, reuse the same client ID and secret, and authorize each connector once.

Roles: the connector asks for https://www.googleapis.com/auth/bigquery, but what the AI can read, query or change is decided by the signed-in account's roles. To run queries the account needs BigQuery Job User on the project that runs them and BigQuery Data Viewer on the data.

Read-only setup: Google offers no BigQuery read-only scope for this API. Change the scope in the connector's OAuth settings to https://www.googleapis.com/auth/cloud-platform.read-only, authorize again, give the account only BigQuery Data Viewer and BigQuery Job User, and disable bigquery_cancel_job. Statements that change data then fail with 403.

Exploring is free: listing projects, datasets and tables, reading a schema with bigquery_get_table and looking at sample rows with bigquery_preview_table_rows scan no bytes. The AI reads the schema before it writes SQL.

Queries cost money, so the AI dry-runs first: on on-demand pricing BigQuery bills the bytes a query scans, about 6.25 US dollars per TiB in most regions (the first TiB each month is free). Before it runs a query on a table it has not sized, the AI runs a free dry run, tells you the estimate in GB and the approximate cost, and asks you to confirm anything above 10 GB, with suggestions to narrow it (fewer columns, a partition filter, a shorter date range). It then sets a byte limit slightly above the estimate, so a query that would bill more fails without charge. LIMIT does not reduce the bytes scanned.

Statements that change data wait for your yes: bigquery_run_query can run any GoogleSQL statement the account is allowed to run, including INSERT, UPDATE, DELETE, MERGE, CREATE, ALTER and DROP. Before anything other than a SELECT, the AI shows you the exact statement and its effect and waits for an explicit yes. Cancelling a running job with bigquery_cancel_job asks first too.

Results and history: a query returns up to 100 rows by default (1,000 at most); the AI pages on with bigquery_get_query_results, which also waits for long queries. bigquery_list_jobs and bigquery_get_job show past jobs with their SQL, bytes processed and billed, and errors.

Common errors: 401 means the authorization expired or was revoked (always after 7 days while the consent screen is in Testing): click Authorize with Provider again. 403 accessDenied: the account lacks a role (Job User on the query project, Data Viewer on the data), or a read-only scope was used for a change. 403 "BigQuery API has not been used in project": enable the BigQuery API in the Cloud project of the OAuth client. 403 bytesBilledLimitExceeded: the query would have scanned more than the limit, and nothing was charged. 400 invalidQuery: an SQL error, and the message names the position. 404 notFound: a wrong project, dataset or table id, or a job looked up without its location. 403 quotaExceeded or rateLimitExceeded: wait and try again.

The connector does not load or export data, copy tables, manage BigQuery ML models or scheduled queries, or use the Storage Read API. It creates or deletes datasets and tables only through SQL statements in a query, after your confirmation.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

1. Go to chatgpt.com/plugins, click +, then Add custom MCP server.
2. Enter a name, e.g. Name: Google BigQuery.
3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

Example prompts

• "Which datasets are in our analytics project, and what columns does the events table have?"
• "Show me ten sample rows of the orders table without running a query."
• "How many orders per country did we have last month? Dry-run the query first and tell me how much data it scans."
• "Which of my BigQuery queries this week billed the most bytes, and what did they run?"
• "In the public dataset bigquery-public-data.samples.shakespeare, which ten words appear most often in Hamlet? Tell me the estimated cost before you run it."

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

• Connector landing page
• Connect to Claude
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse