Skip to main content
This guide shows you how to configure the Databricks connector for WRITER Agent. After setting up this connector, WRITER Agent can perform operations like querying Databricks SQL, accessing Unity Catalog functions, and interacting with Genie spaces through Databricks’ managed MCP servers.
Databricks managed MCP servers are currently in Beta. Workspace administrators control access to this feature through the Databricks Previews page. If you don’t see MCP servers available in your workspace, ask a workspace admin to enable the Managed MCP Servers preview.

​
Set up the Databricks connector

Configure the Databricks connector in AI Studio under Connectors & Tools. The Databricks connector requires a personal access token to authenticate with a Databricks-managed MCP server.
The Databricks connector only supports organization-managed authentication. WRITER-managed authentication is not available for Databricks.

​
Obtain your Databricks MCP server URL

Before configuring the connector in AI Studio, locate your MCP server endpoint in your Databricks workspace:
  1. Log in to your Databricks workspace
  2. Navigate to Workspace → Agents → MCP Servers
  3. Select the managed MCP server you want to connect (for example, SQL or Genie)
  4. Copy the MCP server endpoint URL for use in AI Studio The URL format depends on the type of MCP server:
    Server typeExample URL format
    Vector searchhttps://<workspace-hostname>/api/2.0/mcp/vector-search/{catalog}/{schema}
    DBSQLhttps://<workspace-hostname>/api/2.0/mcp/sql
    Genie spacehttps://<workspace-hostname>/api/2.0/mcp/genie/{genie_space_id}
    Unity Catalog functionshttps://<workspace-hostname>/api/2.0/mcp/functions/{catalog}/{schema}
For more details about Databricks managed MCP servers, see Databricks MCP documentation.

​
Create a Databricks personal access token

Generate a personal access token to authenticate the connector:
  1. In your Databricks workspace, select your username in the top-right corner
  2. Select Settings from the dropdown menu
  3. Navigate to Developer → Access tokens
  4. Select Generate new token
  5. Enter a description (for example, “WRITER MCP connector”)
  6. Set the token lifetime or leave blank for no expiration
  7. Select Generate and copy the personal access token for use in AI Studio
For detailed instructions, see Databricks personal access tokens documentation.

​
Configure the connector in AI Studio

After obtaining your MCP server URL and personal access token:
  1. Navigate to Connectors & Tools in AI Studio
  2. Select the Databricks connector
  3. Select who has access by default (all users or specific teams)
  4. Enter your Databricks MCP server endpoint URL as the tenant URL
  5. Enter your personal access token as the API Key

​
Next steps