Databricks MCP Server logo

Databricks MCP Server

by JustTryAI

The Databricks MCP Server provides access to Databricks functionality via the Model Completion Protocol (MCP). It allows LLM-powered tools to interact with Databricks clusters, jobs, notebooks, and more.

View on GitHub

Last updated: N/A

What is Databricks MCP Server?

The Databricks MCP Server is an implementation of the Model Completion Protocol (MCP) that exposes Databricks functionality through a standardized interface. This allows Large Language Models (LLMs) and other AI tools to interact with Databricks resources such as clusters, jobs, and notebooks.

How to use Databricks MCP Server?

To use the server, first install the necessary prerequisites (Python 3.10+ and uv). Then, clone the repository, set up a virtual environment using uv, and install the dependencies. Configure environment variables for Databricks authentication (DATABRICKS_HOST and DATABRICKS_TOKEN). Finally, start the server using the provided scripts. Once running, LLM-powered tools can interact with the server using the MCP protocol.

Key features of Databricks MCP Server

  • MCP Protocol Support

  • Databricks API Integration

  • Tool Registration

  • Async Support

Use cases of Databricks MCP Server

  • Automating Databricks cluster management

  • Orchestrating Databricks jobs through LLMs

  • Integrating Databricks notebooks into AI workflows

  • Enabling natural language interaction with Databricks resources

FAQ from Databricks MCP Server

What is the MCP protocol?

The Model Completion Protocol (MCP) is a standardized protocol for interacting with models and tools, enabling LLMs to leverage external functionalities.

What Databricks resources can I access through this server?

You can access clusters, jobs, notebooks, and files within DBFS, as well as execute SQL statements.

How do I authenticate with Databricks?

You need to set the DATABRICKS_HOST and DATABRICKS_TOKEN environment variables with your Databricks instance URL and personal access token, respectively.

What are the prerequisites for running this server?

You need Python 3.10 or higher and the uv package manager.

How do I contribute to this project?

Contributions are welcome! Ensure your code follows the project's coding standards, add tests for new functionality, update documentation, and verify all tests pass before submitting a pull request.