Does connecting Snowflake to Rig move my data?

No. Rig runs queries against your own Snowflake compute with a read-only role. Results are returned to the asking user; the underlying data stays in your account.

Can I query Snowflake data in Claude or ChatGPT through Rig?

Yes. Rig serves your Snowflake warehouse to AI assistants over MCP, so you can ask questions in Claude, Claude Code, Cursor, ChatGPT and others and get governed SQL answers.

How does Rig avoid wrong numbers on Snowflake?

Rig builds a context layer over your tables, joins and metric definitions, then validates each generated query in a sandbox before running it. It reasons over modelled definitions rather than guessing column names.

Do Snowflake permissions still apply?

Yes. Role-based access, row-level security and column masking from Snowflake carry through, and Rig adds its own access controls on top.

Warehouses & databases Supported

Snowflake integration for Rig

The easiest way to query Snowflake in Claude and other AI tools

Snowflake is a cloud data warehouse where teams store and query their analytics data across separate compute and storage.

Try Rig Book a demo

What Rig sees in Snowflake

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

Databases
Schemas
Tables and views
Materialized views
dbt models
Warehouse usage and query history

How Snowflake connects to Rig

Rig connects to Snowflake with a read-only role and warehouse, reads your information schema, and builds a context layer over your tables, joins and metric definitions. Queries run as Snowflake SQL against your own compute, so data never leaves your account.

Let business teams query Snowflake without writing SQL

Rig turns a plain-English question into validated Snowflake SQL using your real schema, joins and metric definitions. A revenue lead can ask for last quarter's net revenue retention and get the same number a data analyst would write, because Rig reasons over the modelled tables rather than guessing column names.

Ask Rig

What was our net revenue retention last quarter from the Snowflake finance schema?
Show monthly active accounts by plan for the last 12 months
Which customer segments grew fastest this year?

Explore Snowflake data inside Claude, Cursor or ChatGPT

Rig exposes your Snowflake warehouse to AI assistants over MCP. The assistant sees your governed schema and metric catalog, not raw table dumps, so answers stay grounded in how your team actually defines revenue, churn and active users.

Ask Rig

Break down ARR by region using our Snowflake models
Find the join path from orders to marketing attribution
Why did signups dip in March? Pull the numbers from Snowflake

Control Snowflake cost and access with row-level governance

Because Rig runs read-only and validates every query in a sandbox before it touches your warehouse, you avoid runaway scans and unbounded queries. Role-based access and column masking carry through from Snowflake, so each user only queries what they are allowed to see.

Ask Rig

Which queries scanned the most data this week?
Show warehouse credit usage by team for the last 30 days
List the tables this user is allowed to query

Trace a metric back to its dbt model and source

Rig keeps dbt lineage alongside the warehouse schema, so when someone asks how a number is built, the assistant can walk from the metric to the model to the raw Snowflake table. That ends the recurring argument about whose definition of the metric is right.

Ask Rig

How is active customer defined and which dbt model produces it?
What feeds the revenue table in Snowflake?
Show the lineage for monthly recurring revenue

Ask your Snowflake data in Claude, ChatGPT or Cursor

Rig serves your Snowflake data to AI assistants over MCP. Once Snowflake 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

Does connecting Snowflake to Rig move my data?: No. Rig runs queries against your own Snowflake compute with a read-only role. Results are returned to the asking user; the underlying data stays in your account.
Can I query Snowflake data in Claude or ChatGPT through Rig?: Yes. Rig serves your Snowflake warehouse to AI assistants over MCP, so you can ask questions in Claude, Claude Code, Cursor, ChatGPT and others and get governed SQL answers.
How does Rig avoid wrong numbers on Snowflake?: Rig builds a context layer over your tables, joins and metric definitions, then validates each generated query in a sandbox before running it. It reasons over modelled definitions rather than guessing column names.
Do Snowflake permissions still apply?: Yes. Role-based access, row-level security and column masking from Snowflake carry through, and Rig adds its own access controls on top.