How does Rig get access to my bucket?

Rig gives your workspace a Google service account. You grant it the Storage Object Viewer role on the bucket, so Rig can read that bucket and nothing else, and you can revoke it from the bucket's permissions at any time. A service-account key of your own also works.

What file types does Rig read from Cloud Storage?

CSV, Parquet, JSONL and Excel files load as rows. PDFs, Word documents and text files load as searchable text.

Can I query Cloud Storage files in Claude or ChatGPT?

Yes. Once the files are in your warehouse, Rig serves them to Claude, ChatGPT, Cursor and other AI tools over MCP.

How often does Cloud Storage data refresh?

Rig Ingest syncs on a schedule you set. Each sync reads only files that are new or changed since the last one.

Files & productivity Supported

Google Cloud Storage integration for Rig

The easiest way to connect Google Cloud Storage to Claude and other AI tools

Google Cloud Storage is Google Cloud's object store, where systems and partners drop scheduled exports, data feeds and archives as files in buckets.

Try Rig Book a demo

What Rig syncs from Google Cloud Storage

Once connected, Rig models these objects so questions resolve to the right tables and joins:

CSV files
Parquet files
JSONL files
Excel files
PDF and document text

How Google Cloud Storage connects to Rig

Grant Rig's workspace service account Storage Object Viewer on the bucket, then point Rig at a bucket path and a file pattern. Rig Ingest loads every matching file into one warehouse table and, on each sync, reads only the files that are new or changed.

Read the step-by-step Google Cloud Storage setup guide

Turn a folder of scheduled exports into one table

Systems without an API often export a file a day into a bucket, and the data sits there unread. Rig loads every matching file into a single table on each sync, so a month of daily exports becomes one table you can query and trend.

Ask Rig

Show totals by day across every export in the bucket this month
Which days are missing an export file?
How did yesterday's figures compare to the same day last week?

Join partner and vendor feeds to warehouse data

Partners frequently deliver data by writing files to a bucket. Once those files are a warehouse table, Rig joins them to your own systems, so a vendor feed can be reconciled against the data you already hold.

Ask Rig

Reconcile the partner's settlement file against our orders
Which customers in the vendor feed are missing from our CRM?
Compare the supplier's stock file to our inventory levels

Make archived files queryable without a pipeline

Parquet and CSV archives in Cloud Storage usually need an engineer and a load job before anyone can ask a question of them. Rig reads them directly into the warehouse on a schedule, so the archive becomes queryable without building and maintaining that job.

Ask Rig

Summarise last quarter's archived event files by type
What was the row count of each monthly archive this year?
Find records in the archive for this customer

Ask your Google Cloud Storage data in Claude, ChatGPT or Cursor

Rig serves your Google Cloud Storage data to AI assistants over MCP. Once Google Cloud Storage is synced into your warehouse, you can ask questions in plain English from the tool you already use, and every answer is backed by validated, governed SQL.

Frequently asked questions

How does Rig get access to my bucket?: Rig gives your workspace a Google service account. You grant it the Storage Object Viewer role on the bucket, so Rig can read that bucket and nothing else, and you can revoke it from the bucket's permissions at any time. A service-account key of your own also works.
What file types does Rig read from Cloud Storage?: CSV, Parquet, JSONL and Excel files load as rows. PDFs, Word documents and text files load as searchable text.
Can I query Cloud Storage files in Claude or ChatGPT?: Yes. Once the files are in your warehouse, Rig serves them to Claude, ChatGPT, Cursor and other AI tools over MCP.
How often does Cloud Storage data refresh?: Rig Ingest syncs on a schedule you set. Each sync reads only files that are new or changed since the last one.