Google BigQuery MCP server: ask questions, get governed answers

Google BigQuery AI analytics: what you can ask

Typical questions from analytics and data teams. Each answer shows the definition, source and query behind it.

• What was net revenue by region last quarter, using our approved revenue definition?
• Which top 10 customers drove the most revenue this year?
• Which product lines had the largest margin change month over month?
• How many new customers signed up each week over the past 90 days?
• Compare order volume this month with the same month last year.
• Which tables in our sales dataset have the most rows with missing region values?

Worked example: a governed Google BigQuery answer

One question, and everything the answer shows so you can check it. The figures are invented sample data.

SELECT DATE_TRUNC(DATE(signup_ts, "America/New_York"), WEEK(MONDAY)) AS week,
       COUNT(DISTINCT customer_id) AS new_customers
FROM `analytics.customers`
WHERE signup_ts >= TIMESTAMP_SUB(CURRENT_TIMESTAMP(), INTERVAL 42 DAY)
  AND NOT is_test
GROUP BY week
ORDER BY week;

Common pitfalls when asking Google BigQuery questions

Each one is settled once in an approved definition, so every person and every assistant gets the same answer.

• Partition filters and bytes scanned

  BigQuery bills by bytes scanned. A definition that filters on the partition column keeps every question from reading the whole table.

• Weeks start on Sunday by default

  WEEK in BigQuery means WEEK(SUNDAY). Reporting weeks that start Monday need WEEK(MONDAY), or every weekly number shifts by a day.

• Timestamps are UTC

  TIMESTAMP values are stored in UTC. Converting to the reporting time zone before truncating keeps late-evening signups in the right day.

How Nexatron connects to Google BigQuery

Whose permissions

Questions run through the connection's Google BigQuery account, so its grants are the outer limit. Inside that, Nexatron roles and the row policies your administrator defines decide what each person can see.

Read and write

Read-only. Nexatron reads Google BigQuery data to answer questions and never writes to Google BigQuery.

Setup

An administrator connects a service credential (API token or service-account key) issued by the vendor. Steps: choose the source → check prerequisites → enter connection details → verify → ask. No data migration and no pipeline to build: data is queried where it lives.

Google BigQuery MCP connector for Claude, ChatGPT and Copilot

Nexatron's hosted MCP server is a governed Google BigQuery MCP connector: Claude, ChatGPT and Microsoft Copilot ask questions of your Google BigQuery data through it. Each person signs in as themselves, so the assistant sees only what they may see.

Connect Google BigQuery to Claude, ChatGPT or Copilot

1. Connect Google BigQuery to your Nexatron workspace.
2. In Claude, add Nexatron from Claude's connector directory. In ChatGPT or Copilot, add a custom MCP connector with the server URL https://api.nexatron.io/api/v1/mcp.
3. Sign in with your own Nexatron identity (OAuth 2.1), then ask your Google BigQuery questions.

Google BigQuery connector FAQ

Can I ask Google BigQuery questions without writing queries?

Yes. The connector is available now. Ask in Teams, Slack, the Nexatron web app, or an AI assistant connected through Nexatron's MCP server.

Does Nexatron respect Google BigQuery permissions?

Yes. The Google BigQuery account's grants are the outer limit, and your row policies narrow it for each person.

Can Nexatron change data in Google BigQuery?

No. Nexatron only reads Google BigQuery data.

What do I need to connect Google BigQuery?

A vendor-issued service credential and an administrator to connect it.

Is there a Google BigQuery MCP server for Claude, ChatGPT or Copilot?

Yes: Nexatron's hosted MCP server, once Google BigQuery is connected to your workspace. It is Nexatron's server, not one published by Google BigQuery, and the assistant gets the same governed answer as the Nexatron app.

How is Nexatron different from BigQuery's built-in AI features?

BigQuery's AI features help people working in Google Cloud. Nexatron gives everyone else governed answers in Teams, Slack, the web app or a connected assistant, with approved definitions and the SQL shown, across BigQuery and your other systems.

Which Google Cloud identity runs Nexatron's BigQuery queries?

An administrator connects one service account for the workspace; its dataset permissions are the outer limit. Inside that, Nexatron roles and row policies decide what each person can see.