--- title: "Databricks Integration for Rig: Query Databricks Data in Plain English" description: "Connect Databricks to Rig and query your Databricks data in plain English, or ask it in Claude, ChatGPT and Cursor. Governed, validated answers from your warehouse." canonical: "https://rig.so/integrations/databricks" format: markdown --- Browse integrations ![Databricks logo](https://img.logo.dev/databricks.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=112&format=png&retina=true) Warehouses & databases Supported # Databricks integration for Rig ## The easiest way to query Databricks in Claude and other AI tools Databricks is a data lakehouse platform where teams store and query analytics data, with Delta tables governed by Unity Catalog and served through SQL warehouses. [Try Rig](https://app.rig.so/signup)[Book a demo](https://rig.so/book-demo) ## What Rig sees in Databricks Once connected, Rig models these objects so questions resolve to the right tables and joins: - Unity Catalog catalogs - Schemas - Tables and views - Delta tables - dbt models - Query history - SQL warehouse usage ## How Databricks connects to Rig Rig connects to a Databricks SQL warehouse with a read-only identity, reads Unity Catalog, and builds a context layer over your tables, joins and metric definitions. Queries run as Databricks SQL against your own compute, so data never leaves your workspace. ## Let business teams query Databricks without writing SQL Rig turns a plain-English question into validated Databricks 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 an 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 finance catalog? - Show monthly active accounts by plan for the last 12 months - Which customer segments grew fastest this year? ## Explore Databricks data inside Claude, Cursor or ChatGPT Rig exposes your Databricks lakehouse 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 Databricks models - Find the join path from orders to marketing attribution - Why did signups dip in March? Pull the numbers from Databricks ## Govern Databricks access with Unity Catalog carried through Because Rig runs read-only and validates every query in a sandbox before it touches your SQL warehouse, you avoid runaway scans and unbounded queries. Unity Catalog grants and column masking carry through, so each user only queries what they are allowed to see. Ask Rig - Which queries scanned the most data this week? - Show SQL warehouse 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 Unity Catalog schema, so when someone asks how a number is built, the assistant can walk from the metric to the model to the raw Delta 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 Databricks? - Show the lineage for monthly recurring revenue ## Ask your Databricks data in Claude, ChatGPT or Cursor Rig serves your Databricks data to AI assistants over MCP. Once Databricks 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. - [Claude](https://rig.so/integrations/claude) - [Claude Code](https://rig.so/integrations/claude-code) - [Cursor](https://rig.so/integrations/cursor) - [ChatGPT](https://rig.so/integrations/chatgpt) - [Codex](https://rig.so/integrations/codex) - [Gemini](https://rig.so/integrations/gemini) ## Frequently asked questions Does connecting Databricks to Rig move my data? No. Rig runs queries against your own Databricks SQL warehouse with a read-only identity. Results are returned to the asking user; the underlying data stays in your workspace. Can I query Databricks data in Claude or ChatGPT through Rig? Yes. Rig serves your Databricks lakehouse 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 Databricks? 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 Unity Catalog permissions still apply? Yes. Unity Catalog grants, row filters and column masks carry through, and Rig adds its own access controls on top. ## Related integrations [![Amazon Redshift logo](https://img.logo.dev/aws.amazon.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)Amazon RedshiftPlain-English analytics over your Redshift cluster, governed and validated.](https://rig.so/integrations/redshift)[![BigQuery logo](https://img.logo.dev/cloud.google.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)BigQueryAsk questions of your BigQuery datasets from Claude, ChatGPT or Cursor.](https://rig.so/integrations/bigquery)[![Microsoft SQL Server logo](https://img.logo.dev/microsoft.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)Microsoft SQL ServerPlain-English questions over SQL Server and Azure SQL, governed by Rig.](https://rig.so/integrations/sql-server)[![MotherDuck logo](https://img.logo.dev/motherduck.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)MotherDuckPlain-English analytics over MotherDuck and DuckDB, served to any AI tool.](https://rig.so/integrations/motherduck)[![MySQL logo](https://img.logo.dev/mysql.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)MySQLNatural-language access to your MySQL database, or sync it to the warehouse.](https://rig.so/integrations/mysql)[![PostgreSQL logo](https://img.logo.dev/postgresql.org?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)PostgreSQLAsk questions of your Postgres database, or replicate it into your warehouse.](https://rig.so/integrations/postgres) ## Connect Databricks data to AI tools like Claude Rig builds a governed context layer over your data so every team, and every AI tool, asks questions and gets answers they can trust. [Try Rig](https://app.rig.so/signup)[Book a demo](https://rig.so/book-demo) --- - [This page as HTML](https://rig.so/integrations/databricks) - [Site map for language models](https://rig.so/llms.txt) - [API and agent documentation](https://rig.so/developers)