
Databricks
Connect Databricks so the agent can query Unity Catalog through Databricks SQL while it analyzes your data.
Connecting Databricks to Rippit
MCP connector
The agent queries Unity Catalog
Gives Rippit’s agent SQL against Unity Catalog, read-only unless you turn on the write tool. It needs an account-level OAuth application in Databricks first. A workspace admin connects it once under Connections → MCP Servers.
What you can do with the Databricks MCP connector
3actions
2read
1write
Read & Search
Execute SQL Read Only is on by default- Execute SQL Read OnlyRun read-only SQL against Unity Catalog
- Poll SQL ResultFetch results of a long-running query by statement ID
Create & Update
Off until a workspace admin turns them on- Execute SQLRun SQL including INSERT, UPDATE, CREATE TABLE, and ALTER TABLE
Execute SQL runs any SQL, not just reads, in any catalog the connected identity can write to. Leave it off if you only need analysis.
To bring Databricks content into Rippit, use the Bulk API
There’s no built-in data integration for Databricks. Send its data with the Bulk API, from the Rippit CLI, your coding agent or your own script.
Read the Bulk API docsThen you can
- Label every record with AI columns
- Ask questions across every conversation
- Query it as tables
- Join it with your other data
- Run it on a schedule
Your data and creativity is your edge. Put agents on it to maximize it.
Connect your data. Launch agents.
