Custom MCP Server on Databricks Apps

Example - custom MCP server on Databricks Apps

This example shows how to create and launch a custom agent on Databricks Apps. Please note that this example doesn't use any Databricks SDK, and is independent of the mcp package in the root dir of this repo.

Prerequisites

• Databricks CLI installed and configured
• uv

Local development

• run uv sync:

• start the server locally. Changes will trigger a reload:

This will start the server on http://localhost:8000

Deploying a custom MCP server on Databricks Apps

There are two ways to deploy the server on Databricks Apps: using the databricks apps CLI or using the databricks bundle CLI. Depending on your preference, you can choose either method.

Both approaches require first configuring Databricks authentication:

Using databricks apps CLI

To deploy the server using the databricks apps CLI, follow these steps:

Create a Databricks app to host your MCP server:

Upload the source code to Databricks and deploy the app:

Using databricks bundle CLI

To deploy the server using the databricks bundle CLI, follow these steps

Update the app.yaml file in this directory to use the following command:

• In this directory, run the following command to deploy and run the MCP server on Databricks Apps:

Connecting to the MCP server

To connect to the MCP server, use the Streamable HTTP transport with the following URL:

For authentication, you can use the Bearer token from your Databricks profile. You can get the token by running the following command:

Please note that the URL should end with /mcp/ (including the trailing slash), as this is required for the server to work correctly.