- UNIFIED
- AUTOMATED
- DISCOVERABLE
- HUMAN
Short answer
How can I query multiple data sources with one AI prompt?
Your AI uses Starburst to execute SQL across diverse sources like S3, Snowflake, and Iceberg through a single interface. It identifies available catalogs and data products to find exactly what you need. You get a unified view of your entire data estate.
The outcomes.
Where your data becomes accessible.
Once connected, your AI handles the heavy lifting of locating and reading data.
UNIFIED
One interface for all data
The AI treats Snowflake, S3, and Iceberg as one place. You don't have to switch tools to find information.
AUTOMATED
SQL generation and execution
Your agent writes the SQL to pull data from different sources. It handles the translation between your question and the storage.
DISCOVERABLE
Instant data discovery
The AI scans your connected catalogs to see what's available. It finds the specific tables or products required for your prompt.
HUMAN
Review and refine results
The AI presents the data it found. You decide if the query was accurate or if the results need more filtering.
The workflow
What your AI does when the request arrives.
The AI moves from discovery to execution using the Starburst connection.
Locate data sources
The agent looks through all connected environments to see which catalogs are reachable.
list_catalogsIdentify specific products
It narrows down the search to find the exact data products needed for your question.
list_data_productsGenerate SQL
Your AI writes the SQL query required to join or filter data across those specific sources.
list_catalogsDeliver answers
The agent pulls the final result set from the federated layer and presents it to you.
list_data_products
Try it
Copy these to start.
Use these prompts to begin querying your data.
Starting points
These are opening lines. Swap out the specific table or catalog names for your own.
Starburst Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_O3fkMMqaRDxXU8YcUOdnSQyixPMchBfro4bAKlB1/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Starburst capabilities are ready to use.
{
"mcpServers": {
"starburst-mcp": {
"url": "https://edge.vinkius.com/vk_preview_O3fkMMqaRDxXU8YcUOdnSQyixPMchBfro4bAKlB1/mcp"
}
}
}List all the data catalogs available through Starburst.
Find the data products in the sales catalog and show me the last ten entries.
Query the Iceberg tables to find total revenue for Q3.
Compare the user counts in Snowflake with the activity logs in S3.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Starburst once, then ask.
Follow the link to connect your Starburst instance. Your credentials stay encrypted and secure, and you can immediately start chatting with your data.
Connect Starburst to your AIFAQ
How Starburst querying behaves
- 01
Can the AI delete data in my Snowflake warehouse?
No. The AI only has tools to list catalogs and data products. It cannot execute write, update, or delete commands.
- 02
Does the AI move my data to a new location?
No. The data stays exactly where it is in S3, Snowflake, or Iceberg. The AI only queries it through the Starburst interface.
- 03
How does the AI know which tables to use?
It uses the list_catalogs and list_data_products tools to see what is available before it attempts to write a query.
- 04
Can I use this with any AI client?
Yes, as long as the client is MCP-compatible, like Claude, Cursor, or Windsurf.
- 05
Will the AI manage my Starburst permissions?
No. The AI respects the permissions already set up in your Starburst environment. It can only see what your existing credentials allow.
More questions about Starburst? See everything the Starburst Connector can do
Connect Starburst to Claude, Cursor, ChatGPT & more
