Sequel

Connectors

BigQuery

Connecting Google BigQuery to Sequel

This guide walks you through connecting your Google BigQuery data warehouse to Sequel. Once connected, you can query petabytes of data in plain English, visualize results as charts, and use BigQuery as a data source in Claude Code, Claude Desktop, and other AI tools via Sequel's MCP server.

Prerequisites

Before you begin, make sure you have:

  • A Google account with access to a GCP project that has BigQuery enabled
  • BigQuery API enabled in your GCP project (enable it here)
  • A Sequel account — sign up at sequel.sh
  • Your GCP Project ID — visible in the Google Cloud Console dashboard

Step 1: Navigate to Data Sources

  1. Sign in to sequel.sh.
  2. Click Data Sources in the left sidebar.
  3. Click New Connection.

Step 2: Select BigQuery

From the list of available connectors, select BigQuery.

Step 3: Authorize with Google OAuth

Click Connect with Google. You will be redirected to Google's sign-in page.

  1. Sign in with the Google account that has access to your BigQuery project.
  2. Review the permissions — Sequel requests read-only access (bigquery.readonly scope) only.
  3. Click Allow.

You will be redirected back to Sequel.

Step 4: Enter Your GCP Project ID

After authorizing, enter your GCP Project ID (e.g. my-company-analytics-123).

You can find your project ID in the Google Cloud Console — it appears in the project selector at the top of the page.

Click Connect to verify the connection and save it.

Step 5: Query Your Data

Once connected, Sequel reads your BigQuery schema (datasets and tables) and generates instructions for the AI. You can now ask questions like:

  • "What are the top 10 products by revenue this month?"
  • "Show me daily active users for the past 30 days as a line chart"
  • "Which campaigns drove the most conversions last week?"

Sequel converts your question into a BigQuery standard SQL query, runs it, and displays the results.

Step 6: Visualize Results

Ask Sequel to visualize any query result:

  • "Show me user growth over the last 6 months as a line chart"
  • "Give me a bar chart of revenue by country this quarter"
  • "Pie chart of sessions by device type today"

Troubleshooting

Access denied (403) Make sure the BigQuery API is enabled for your GCP project and that your Google account has the BigQuery Data Viewer role or bigquery.dataViewer IAM permission.

Project not found (404) Double-check your GCP Project ID — it should be the project identifier, not the project name or number. Example: my-company-analytics-123, not My Company Analytics or 123456789.

No datasets visible Your Google account must have at least BigQuery Data Viewer on the dataset or project level. Ask your GCP administrator to grant this role.

Query costs BigQuery charges based on bytes scanned. For large partitioned tables, add instructions in your connection settings to always filter by the partition column (e.g. Always filter by event_date when querying the events table).

Restricting Access to Specific Datasets

AI assistants work best when they focus on a targeted set of tables. You can limit Sequel's schema introspection to specific datasets:

  1. Open the connection in Data Sources.
  2. Go to the Schema tab.
  3. Select the datasets you want Sequel to use.

This ensures the AI only sees the tables relevant to your questions.

Creating a Read-Only BigQuery User (Recommended)

For production use, it's best practice to create a dedicated service identity or use a restricted Google account:

1. Create a service account (optional)

If you prefer service account authorization (not yet supported via OAuth), grant it:

gcloud projects add-iam-policy-binding YOUR_PROJECT_ID \
  --member="serviceAccount:sequel@YOUR_PROJECT_ID.iam.gserviceaccount.com" \
  --role="roles/bigquery.dataViewer"

2. Grant read-only access at dataset level

To restrict access to specific datasets rather than the whole project:

  1. Go to BigQuery in the Cloud Console.
  2. Select your dataset → click Share → Add principal.
  3. Enter your Google account email.
  4. Assign the BigQuery Data Viewer role.
  5. Click Save.

This ensures your Sequel connection can only read from the datasets you explicitly share.

Conclusion

You've connected Google BigQuery to Sequel. You can now use natural language to explore your data warehouse, create visualizations, and power AI tools with live BigQuery data.

For questions or help, contact Sequel support.

Additional Resources

MotherDuckDigital Ocean