Unity Catalog tables and Databricks SQL queries on a SQL warehouse. Changes wait for approval.
The screenshots show GateRook 2.0.0: the Databricks SQL form, the endpoint selector, and this connector’s actual tool preview. The form and preview have not been saved. Select a screenshot to open it at full size.
1. Create a connection and enter the settings
In GateRook, open Connections, select Add connection, search for Databricks SQL, choose its card and select Continue to configure.
Open the SQL warehouse’s connection details and copy the workspace URL and warehouse ID. The ID is the final part of its /sql/1.0/warehouses/ HTTP path.
Prepare an OAuth machine-to-machine service principal or a personal access token. The identity needs permission to use the warehouse and read the chosen catalogs, schemas and tables.
Enter a Name, for example databricks-demo. Your AI app uses this name to choose the connection.
Enter Workspace URL including https:// and the SQL warehouse ID. This is the warehouse ID, not the full HTTP path.
Under Sign in with, choose the service-principal option and enter Client ID and Client secret, or choose A personal access token and enter Personal access token.
Use Default catalog and Default schema for unqualified names. Narrow Catalogs and Schemas to the datasets you intend the AI to use.
Choose Development, Staging or Production to match the service. Review the connector’s limit and access settings before continuing.
2. Test the connection and add it to an endpoint
Select Continue to test. GateRook checks the settings from your computer. Review the result and resolve any connection, certificate or permission error before continuing.
If a query is refused, verify CAN USE on the warehouse and the applicable USE CATALOG, USE SCHEMA and SELECT grants. Check that the token or OAuth secret belongs to the workspace in Workspace URL.
After the test passes, select Continue to add to an endpoint. Choose the endpoint your AI app uses, review its tool modes, then select Save connection. GateRook offers default as the starter endpoint.
3. Use the connection from your AI IDE
After saving Databricks SQL on the endpoint and passing its connection test, ask your AI app to use databricks-demo, or the name you chose. If its tools are missing, confirm the endpoint assignment and refresh the MCP connection or start a new chat.
The preview below shows this connector’s default tools before saving. The table explains what each tool can do; connection settings, credentials and endpoint policies can restrict access further.
Start with a small read request. Replace example resource names with existing resources your connection may access. Open Activity after the call to inspect its connection, tool, arguments, policy decision and result metadata.
Ask your AI, for example
- “List the catalogs available through databricks-demo.”
- “Describe the columns of main.analytics.orders on databricks-demo.”
- “Using databricks-demo, count orders by status in main.analytics.orders.”
| Tool | What it does | Starts as |
|---|---|---|
databricks_list_catalogs | Unity Catalog catalogs agents may use. | Read only |
databricks_list_schemas | Schemas agents may use in one catalog. | Read only |
databricks_list_tables | Tables, views and their kinds in one schema. | Read only |
databricks_describe_table | Columns with their types, partitioning, format and comment of one table or view. | Read only |
databricks_query | One SELECT, WITH, VALUES, SHOW, DESCRIBE or EXPLAIN on the connection's SQL warehouse. Values as :name parameters. Pages with nextCursor. | Read only |
databricks_execute | One INSERT, UPDATE, DELETE, MERGE, DDL or table maintenance statement. You approve the exact text. | Approval |
You can change each tool’s mode on the endpoint. Every call your AI makes appears in Activity.