Amazon Redshift integration for Rig
The easiest way to query Amazon Redshift in Claude and other AI tools
Amazon Redshift is AWS's petabyte-scale cloud data warehouse for running SQL analytics across structured and semi-structured data.
What Rig sees in Amazon Redshift
Once connected, Rig models these objects so questions resolve to the right tables and joins:
- Schemas and tables
- Views and late-binding views
- Materialized views
- dbt models
- Spectrum external tables
- STL query history
How Amazon Redshift connects to Rig
Rig connects to Redshift with a read-only user, reads the system catalog, and builds a context layer over your tables, joins and metrics. Queries run as Redshift SQL against your cluster or serverless workgroup.
Answer business questions over Redshift without SQL
Rig converts a plain-English question into Redshift SQL using your modelled schema and metric definitions. It respects distribution and sort keys in how it shapes queries, so analysts get correct answers and the cluster is not hammered by naive joins.
- What was gross margin by product category last quarter?
- Show weekly order volume by region from Redshift
- Which cohorts have the highest repeat purchase rate?
Query Redshift Spectrum and S3 data lake tables
When part of your data lives in S3 via Redshift Spectrum, Rig treats external tables as part of the same context layer. You can ask questions that span warehouse tables and lake tables without knowing which is which.
- Join clickstream in S3 to orders in Redshift
- What is the average session length from the Spectrum events table?
- Show revenue alongside raw event counts
Serve Redshift data to Claude, Cursor and ChatGPT
Rig exposes Redshift to AI assistants over MCP with governance attached. The assistant sees your metric catalog and join paths, so it answers from agreed definitions rather than improvising SQL against raw tables.
- Pull net revenue retention from Redshift
- Find the path from subscriptions to invoices
- Why did churn rise last month? Use the Redshift models
Keep Redshift queries safe and bounded
Every Rig query is validated in a sandbox before it runs, with limits applied, so an open-ended question never locks up the cluster. Read-only access and inherited permissions keep each user inside their lane.
- Which queries ran longest on the cluster this week?
- Show concurrency scaling usage for the last 30 days
- List tables this analyst can read
Ask your Amazon Redshift data in Claude, ChatGPT or Cursor
Rig serves your Amazon Redshift data to AI assistants over MCP. Once Amazon Redshift 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 Rig support Redshift Serverless?
- Yes. Rig connects to both provisioned Redshift clusters and Redshift Serverless workgroups with a read-only user.
- Can Rig query Redshift Spectrum external tables?
- Yes. External tables on S3 are part of the same context layer, so questions can span warehouse and data-lake tables.
- How does Rig protect the cluster from heavy queries?
- Rig sandbox-validates each query and applies limits before running it, and it shapes SQL with distribution and sort keys in mind to avoid naive scans.
- Can I ask Redshift questions in Claude or ChatGPT?
- Yes. Rig serves Redshift to AI assistants over MCP so you can ask in plain English from your assistant of choice.
Related integrations
Connect Amazon Redshift 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.