• DATA
  • SEGMENTS
  • SCHEMA
  • HUMAN

How to run adhoc SQL queries with your AI

Connect your AI to BigQuery once. After that, you can query your datasets using plain English.

Ask AI about this page

Short answer

Can I query BigQuery with natural language?

Yes. Your AI translates your English requests into Standard SQL to pull specific rows or segments from your tables. You get the data results directly in your chat interface.

The results you get

What your queries produce

The AI handles the syntax so you can focus on the data.

DATA

Instant data pulls

The AI writes and runs the SQL for you. You get the specific rows or counts you asked for without touching a query editor.

SEGMENTS

Targeted user cohorts

Ask for specific groups, like users who signed up last week. The AI filters your BigQuery tables to find them.

SCHEMA

Table structure awareness

The AI looks at your table definitions to understand column names and types. This ensures the SQL it writes actually works.

HUMAN

Manual verification

You stay in control. You can review the generated SQL or the resulting data to make sure it matches your expectations.

The workflow

What your AI does when a request arrives.

The AI moves from understanding your question to delivering the data.

  1. Inspect your data

    The AI looks at your BigQuery table structures to see what columns and data types are available.

    get_table

  2. Write the SQL

    It converts your English request into a valid Standard SQL statement based on the table schema it just read.

    get_table

  3. Run the query

    The AI sends the generated SQL to BigQuery to fetch the actual data you asked for.

    execute_query

  4. Deliver results

    The AI presents the resulting data or summary directly in your chat window.

    execute_query

Try it

Copy these to start.

Use these prompts to begin querying your BigQuery data.

Starting points

Replace the bracketed text with your actual table or column names.

Google BigQuery Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_XL1CHYzMkCvLxlGLPBzLHDOTg35sqGtg0BPtLGTY/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Google BigQuery capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "google-bigquery-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_XL1CHYzMkCvLxlGLPBzLHDOTg35sqGtg0BPtLGTY/mcp"
    }
  }
}
Copy into chat04

  • Show me the first 10 rows from the [table_name] table.

  • How many users in the [table_name] table have a 'premium' status?

  • List the most recent 5 entries from [table_name] where the country is 'USA'.

  • Summarize the total revenue from the [table_name] table for the last month.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Google BigQuery once, then ask.

Follow the link to connect your account. Your credentials stay encrypted, and you can start querying immediately in your preferred AI client.

Connect Google BigQuery to your AI

FAQ

How this task behaves

  • 01

    Can the AI delete my data?

    No. The tools provided only allow the AI to read table schemas and execute queries. It cannot perform DELETE or DROP operations.

  • 02

    Does the AI write the SQL for me?

    Yes. It translates your natural language into Standard SQL and runs it using the provided tools.

  • 03

    Can the AI create new tables?

    No. The current capabilities are limited to reading existing tables and executing queries. It cannot create or modify table structures.

  • 04

    Do I need to know SQL to use this?

    No. You can use plain English to ask for the data you need.

  • 05

    How does the AI know which columns to use?

    The AI uses the get_table capability to inspect your table schema before it writes any SQL.

  • More questions about Google BigQuery? See everything the Google BigQuery Connector can do

Connect Google BigQuery to Claude, Cursor, ChatGPT & more