How do I connect my BigQuery data to my AI client?

You subscribe to the MCP on Vinkius and provide your GCP Project ID and an OAuth or Service Account Token. Once connected, your client can immediately start using the capabilities.

Which AI clients can use this BigQuery MCP?

This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can the AI write SQL for me?

Yes, the MCP includes a capability to execute Standard SQL, allowing your agent to write and run queries based on your prompts.

The MCP uses your provided GCP credentials and OAuth/Service Account tokens to ensure all actions are performed within your existing security framework.

Can I use this to troubleshoot failed jobs?

Yes, you can use the capabilities to list recent jobs and read specific error traces to find out why a computation failed.

Can my AI write its own queries if I just ask it a business question?

Yes! The agent will typically use list_tables and get_table to study the columns first. Then, realizing constraints, it will natively invoke execute_query running an optimized Standard SQL string to fetch exactly what you asked for.

Will my prompt fail if it returns millions of rows?

It might hit the context window boundaries of the chosen foundational LLM. Good practice suggests instructing your AI to always append LIMIT 100 initially or run macro aggregations (like COUNT() or SUM()) natively inside BigQuery first.

How do I check if a query was expensive after it ran?

Use the list_jobs or get_job endpoints. They expose metadata directly from Google's history returning the totalBytesProcessed flag so your agent can estimate overhead intelligently.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Google BigQuery to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your AI agent into a high-speed data analyst.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Google BigQuery.

01
List tables
Use this to see all the tables currently sitting inside a specific dataset.
02
Execute query
This capability runs a specific Standard SQL command directly against your data.
03
Get dataset
This capability fetches the exact details and properties of a specific BigQuery dataset.
04
Get job
This capability retrieves the full technical details for a specific BigQuery job run.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Google BigQuery.

05
List datasets
This capability returns a list of all datasets within your active GCP project.
06
Get table
This capability pulls the specific metadata and schema details for a single BigQuery table.
07
List jobs
This capability lets your agent see a list of recent BigQuery runtime jobs.

Real work

What teams actually run

Pipeline Debugging

Check if a background process successfully inserted rows after a deployment.

Rapid Data Prototyping

Ask your agent to find specific user segments using natural language.

Workload Monitoring

Identify heavily delayed computations by checking recent job lists.

Schema Mapping

Quickly inspect table columns and partitioning settings during development.

Automate a task

Put Google BigQuery to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Google BigQuery works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Google BigQuery to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

856ms average. Fast in production.

Google BigQuery is checked daily against the live service.

Daily averagePeak 1061ms

Oct 3Today

Fastest day: 657ms
Slowest day: 1061ms
14-day trend: Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Google BigQuery, so you can see the experience inside your AI.

It does not authenticate your account with Google BigQuery. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

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.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
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"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Google BigQuery in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Google BigQuery owners hand off.

This MCP is built for technical professionals who need to interact with massive datasets without leaving their development environment.

01
Data Engineers
They use it to troubleshoot failing scheduled queries and explore undocumented columns.
02
Marketing Analysts
They use it to request customer cohorts using conversational logic.
03
Backend Developers
They use it to confirm that application pipelines inserted the correct rows.

FAQ

Questions Google BigQuery owners ask.

01
How do I connect my BigQuery data to my AI client?
You subscribe to the MCP on Vinkius and provide your GCP Project ID and an OAuth or Service Account Token. Once connected, your client can immediately start using the capabilities.
02
Which AI clients can use this BigQuery MCP?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can the AI write SQL for me?
Yes, the MCP includes a capability to execute Standard SQL, allowing your agent to write and run queries based on your prompts.
04
Is my data secure?
The MCP uses your provided GCP credentials and OAuth/Service Account tokens to ensure all actions are performed within your existing security framework.
05
Can I use this to troubleshoot failed jobs?
Yes, you can use the capabilities to list recent jobs and read specific error traces to find out why a computation failed.
06
Can my AI write its own queries if I just ask it a business question?
Yes! The agent will typically use list_tables and get_table to study the columns first. Then, realizing constraints, it will natively invoke execute_query running an optimized Standard SQL string to fetch exactly what you asked for.
07
Will my prompt fail if it returns millions of rows?
It might hit the context window boundaries of the chosen foundational LLM. Good practice suggests instructing your AI to always append LIMIT 100 initially or run macro aggregations (like COUNT() or SUM()) natively inside BigQuery first.
08
How do I check if a query was expensive after it ran?
Use the list_jobs or get_job endpoints. They expose metadata directly from Google's history returning the totalBytesProcessed flag so your agent can estimate overhead intelligently.

Explore

More in Industry Titans

Connect Google BigQuery to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

List tables

Execute query

Get dataset

Get job

05-07

List datasets

Get table

List jobs

What teams actually run

Pipeline Debugging

Rapid Data Prototyping

Workload Monitoring

Schema Mapping

Building your own app? The connector is yours to use.

Google BigQuery Connector

Claude Desktop

Data Engineers

Marketing Analysts

Backend Developers

How do I connect my BigQuery data to my AI client?

Which AI clients can use this BigQuery MCP?

Can the AI write SQL for me?

Is my data secure?

Can I use this to troubleshoot failed jobs?

Can my AI write its own queries if I just ask it a business question?

Will my prompt fail if it returns millions of rows?

How do I check if a query was expensive after it ran?

Hevo Data (ETL & Data Pipeline) AI Connector

Matillion (Cloud Data Integration & ELT) AI Connector

Integrate.io (ETL & Data Integration) AI Connector

Snowflake AI Connector

Suggestions

Data Pipeline Prover AI Connector

Snowflake AI Connector

Amazon Redshift AI Connector

data.world AI Connector