How to Connect BigQuery to ChatGPT

Query your BigQuery data directly from ChatGPT using Sequel’s MCP server. Ask questions in plain English, with no SQL, no dashboards, and no context switching.

Short answer

Connect BigQuery to Sequel, then add Sequel's MCP server to ChatGPT using the config on this page. ChatGPT can then query your live BigQuery data in plain English, with no connector code and no CSV exports. Both steps take a few minutes.

Example prompts

Everything you can ask ChatGPT about your BigQuery data.

Ask in plain English — Sequel translates it into a BigQuery query, runs it, and ChatGPT hands back the answer. No SQL, no dashboards, no CSV exports.

What you can ask ChatGPT
  • What are the top 10 events by count this week?
  • Show me daily revenue for the past 30 days as a line chart
  • Which users had the highest session count last month?
  • What's the p95 query latency by dataset over the past 7 days?
  • List all tables in my analytics dataset with row counts

How it works

Three steps to get started

1

Connect BigQuery to Sequel

In your Sequel dashboard, go to Connections and add BigQuery. Sequel handles authentication and schema discovery automatically.

2

Add Sequel to the agent

Copy the Sequel MCP configuration into ChatGPT's settings file (shown below). Swap in your API key from Settings → API Keys.

3

Ask ChatGPT about your data

Restart ChatGPT and start asking questions. "What are the top 10 events by count this week?" — and get a real answer backed by live BigQuery data.

Why ChatGPT

What ChatGPT does with your BigQuery data

Real data, not hallucinations

ChatGPT with Sequel queries your actual databases in real time. Instead of guessing or making up numbers, it fetches accurate data from your connected sources and presents verified results.

Share data insights via ChatGPT conversations

Teams that already use ChatGPT for work can now use it for data questions too. Sequel handles the database access; ChatGPT handles the explanation and formatting.

Analyze data with Python in the same thread

When SQL isn't enough, Sequel's workbench tool lets ChatGPT run Python analyses — statistical summaries, charts, transformations — without leaving the conversation.

Configuration

Add Sequel to ChatGPT

Place this in ChatGPT Settings → Connectors and replace sql_your_api_key with a key from Settings → API Keys.

ChatGPT Settings → Connectors

Server URL:
https://api.sequel.sh/mcp

Authentication:
Authorization: Bearer sql_your_api_key

Install

Install BigQuery MCP in ChatGPT

Pick your app and Sequel installs itself: a one-click link where the client supports it, that client’s own few steps where it doesn’t. Every route signs in with your Sequel account over OAuth, so there is no API key to copy and nothing to keep in sync.

Already have an MCP client?

https://api.sequel.sh/mcp

Add it as a remote (streamable HTTP) server and sign in when prompted. Skills come with it; nothing else to install. Manual setup per client

Add Sequel to ChatGPT

Server URL

https://api.sequel.sh/mcp
  1. 1In Settings → Security and login, turn on Developer mode.
  2. 2Go to chatgpt.com/plugins. Click Add at the top right, then Create MCP app.
  3. 3Name it Sequel and paste the URL under Connection. Leave Authentication on OAuth.
  4. 4Tick “I understand and want to continue”, click Create, then Allow when ChatGPT asks you to sign in.

Frequently asked questions

How do I connect BigQuery to ChatGPT?

You need two things: (1) connect BigQuery to Sequel in your Sequel dashboard under Connections, and (2) add the Sequel MCP config to ChatGPT using the setup shown above. Once both are done, ChatGPT can query your BigQuery data directly.

What BigQuery data can ChatGPT access?

ChatGPT can access any data available through your BigQuery connection in Sequel. Use Sequel's search tool to discover available metrics and dimensions, then execute queries to pull the data you need.

Is my BigQuery data sent to ChatGPT's servers?

Query results are returned to ChatGPT as context within your conversation. Only the data you explicitly ask about is retrieved. Sequel never stores your query results permanently — they exist only for the duration of the tool call.

Do I need a Sequel account?

Yes. You need a Sequel account to connect BigQuery and generate an API key. Sign up free at sequel.sh — no credit card required. Then create a connection to BigQuery and generate an API key from Settings → API Keys.

Can I connect multiple BigQuery accounts?

Yes. Sequel supports multiple connections of the same type. If you have multiple BigQuery accounts or properties, add each as a separate connection in Sequel. ChatGPT will be able to query all of them.

How do I connect Sequel to ChatGPT?

In ChatGPT, go to Settings → Beta Features → Connectors (or Settings → Integrations, depending on your plan). Enter the Sequel MCP URL and your API key as the Authorization header.

Which ChatGPT plans support MCP?

MCP connector support is available on ChatGPT Plus, Team, and Enterprise plans. Check OpenAI's latest documentation for the most current availability.

Can I use Sequel with the ChatGPT API?

Yes — you can pass Sequel as a tool in any OpenAI API request by calling Sequel's MCP endpoint and converting the tool definitions to OpenAI's tool format. Contact us for guidance on this integration.

Is my data stored by OpenAI when I query through ChatGPT?

Query results are sent to OpenAI as context within your conversation and are subject to OpenAI's data handling policies. Review OpenAI's privacy policy for details. Sequel does not store query results.

Do I need a service account key to connect BigQuery?

No. Sequel uses Google OAuth 2.0, so you authorize with your Google account directly — no JSON key files required. Sequel requests read-only access (bigquery.readonly scope) so it can only run SELECT queries.

What is a GCP Project ID and where do I find it?

The GCP Project ID is the unique identifier for your Google Cloud project (e.g. my-company-analytics-123). You can find it in the Google Cloud Console at the top of the dashboard, or by running `gcloud config get-value project` in your terminal.

Does Sequel support BigQuery legacy SQL?

No. Sequel generates standard SQL (GoogleSQL) only. Legacy SQL is deprecated by Google and is not supported.

Will Sequel see all my BigQuery datasets and tables?

Sequel will list all datasets your Google account has access to within the connected project. You can restrict schema introspection to specific datasets from the connection settings after connecting.

Connect BigQuery to ChatGPT today

Sign up free, connect your data sources, and start querying in minutes.