Databricks
BetaQuery the Databricks lakehouse — SQL warehouses, Unity Catalog functions, Genie spaces, and vector search.
- Databricks
- Lakehouse
- Analytics
- Authentication
- API key
- Hosting
- Vendor-hosted endpoint
How it works
Every agent request passes through Ferentin policy before it reaches Databricks.
Ferentin connects to a Databricks managed MCP server on your own workspace host using a personal access token or service-principal OAuth token. Because every endpoint is workspace-scoped, the server URL is supplied at install time. Unity Catalog grants remain the authorization boundary for every tool call.
- AI agentAsks for something
- Ferentin policies
- Unity catalog governance
- Service principal auth
- Workspace scoped endpoint
- Databricks MCP serverAuthorized connection
- Governed resultMasked, logged, returned
What you can do with Databricks
- SQL warehouse query
- Unity catalog functions
- Genie spaces
- Vector search
Before you connect
- The URL shipped with this card is an EXAMPLE host and will not resolve — installing without overriding the endpoint fails to connect.
- Managed MCP servers are in Public Preview; endpoint paths and available servers may change.
- Unity Catalog is the authorization boundary. Ferentin sends one token per instance, so every caller on that instance acts as that single principal — use a least-privilege service principal rather than a workspace admin's PAT.
- Azure Databricks workspaces use an *.azuredatabricks.net host; GCP workspaces use *.gcp.databricks.com.
1 more technical note
- Databricks does not support Dynamic Client Registration on these endpoints, so Ferentin uses token auth rather than an OAuth authorization-code flow.
About Databricks
Databricks is a unified data and AI platform built on the lakehouse architecture, combining data warehousing, ETL, and machine learning on open formats with Unity Catalog providing centralized governance across data and AI assets.
Frequently asked about Databricks
- What can AI agents do with Databricks through Ferentin?
- Through Ferentin, agents can use Databricks for SQL warehouse query, unity catalog functions, genie spaces and vector search. Every call is checked against your Ferentin policies first.
- How is Databricks access secured?
- Requests through the Databricks integration are covered by unity catalog governance, service principal auth and workspace scoped endpoint. These controls are applied by Ferentin, not by Databricks, so they hold across every connected agent.
- How do I connect Databricks to Ferentin?
- Open the Ferentin admin console, add Databricks as a new connection and authenticate with API key. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.
- Is the Databricks integration generally available?
- The Databricks integration is currently beta on Ferentin.
Related integrations
3
Snowflake
Natural-language analytics and governed SQL over Snowflake via Cortex Analyst and Cortex Search.
Google BigQuery
Query and explore BigQuery data warehouses. Discover datasets/tables, inspect schema, and run read-only SQL — governed by Cloud IAM.
Elasticsearch
Search, ES|QL, and index discovery over your Elasticsearch data via Elastic Agent Builder.