databricks-mcp
If you are the rightful owner of databricks-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Completion Protocol (MCP) server for Databricks that provides access to Databricks functionality via the MCP protocol. This allows LLM-powered tools to interact with Databricks clusters, jobs, notebooks, and more.
The Markov Databricks MCP server is a specialized server that implements the Model Completion Protocol (MCP) to facilitate interaction between large language models (LLMs) and Databricks services. By leveraging the MCP protocol, this server enables seamless integration with Databricks clusters, jobs, notebooks, and other resources, allowing for automated and efficient management of Databricks environments. The server is designed with asynchronous support using asyncio, ensuring high performance and responsiveness. It integrates with the Databricks REST API, providing a comprehensive suite of tools for managing Databricks resources. The project is maintained by Olivier Debeuf De Rijcker and is based on an initial version by JustTryAI. The server is particularly useful for developers and data scientists who wish to automate their workflows and enhance their productivity by using AI-driven tools to manage Databricks resources.
Features
- MCP Protocol Support: Implements the MCP protocol to allow LLMs to interact with Databricks
- Databricks API Integration: Provides access to Databricks REST API functionality
- Tool Registration: Exposes Databricks functionality as MCP tools
- Async Support: Built with asyncio for efficient operation
Tools
list_clusters
List all Databricks clusters
create_cluster
Create a new Databricks cluster
terminate_cluster
Terminate Databricks cluster
get_cluster
Get information about a specific Databricks cluster
start_cluster
Start a terminated Databricks cluster
list_jobs
List all Databricks jobs
run_job
Run Databricks job
list_notebooks
List notebooks in the workspace directory
export_notebook
Export notebook from workspace
list_files
List files and directories in DBFS paths
execute_sql
Execute SQL statements
