How is this different from connecting Databricks MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Databricks MCP API changes?

We track the Databricks MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Databricks tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Databricks?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Databricks MCP server myself?

No. TrustGate connects to the Databricks MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Databricks directly.

Connect Databricks MCP to your AI agents, securely.

Q: Is Databricks MCP secure?

The server itself exposes 6 tools, and some of them can write to your Databricks account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Databricks.

One secured endpoint for every Databricks call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Databricks MCP now

What your agents can ask once Databricks MCP is connected.

“What were last quarter's revenues by region?”
“Run this SQL query against the warehouse”
“Search the support knowledge base for this error”

“Run the customer lookup function for this account”
“Validate the syntax of this query”
“Which Genie spaces can I ask questions in?”

Select the tools your AI agents can call

6 tools from the Databricks MCP schema.

Showing 6 tools

system.ai.genie_one_mcpreadAnswers natural-language analytics questions across your workspace with Genie One, grounded in Genie Ontology.
system.ai.dbsqlwriteRuns specific SQL queries for development and data engineering on a SQL warehouse, using the caller's Unity Catalog and warehouse permissions.
ai-searchreadQueries Databricks AI Search indexes in a Unity Catalog schema to find relevant documents. Requires Databricks managed embeddings.
unity-catalog-functionsreadRuns Unity Catalog functions as predefined SQL tools in the specified catalog and schema.
system.ai.sandboxhigh riskRuns Python, SQL, or shell code in an isolated environment. The sandbox has no network egress.
system.ai.web_searchhigh riskSearches the public web and returns a synthesized answer with citations.

What Databricks MCP exposes

Databricks MCP groups its 6 tools into 4 categories, each with a suggested starting policy.

Category	Covers	Access	Suggested policy
Analytics	Natural-language analytics with Genie One, grounded in Genie Ontology	Read	Limit to the intended Genie spaces
SQL	Running specific SQL queries on a warehouse under the caller's Unity Catalog permissions	Read / Write	Approve queries against production warehouses
Data Retrieval	AI Search indexes over unstructured data and Unity Catalog functions	Read	Scope each catalog and schema
Compute & Web	Sandboxed Python, SQL or shell execution and public web search	Read / Write	Approve code execution; the sandbox has no network egress