JustTryAI_databricks-mcp-server
If you are the rightful owner of JustTryAI_databricks-mcp-server 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.
The Databricks MCP Server is designed to facilitate interaction between LLM-powered tools and Databricks clusters, jobs, notebooks, and more through the Model Completion Protocol (MCP). By integrating with the Databricks REST API, it allows for seamless management and execution of Databricks resources. The server is built with asyncio to ensure efficient operation and supports the registration of various Databricks functionalities as MCP tools. This setup enables users to perform tasks such as listing, creating, and managing clusters, executing jobs, and handling notebooks directly through the MCP protocol.
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 a 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 a Databricks job
list_notebooks
List notebooks in a workspace directory
export_notebook
Export a notebook from the workspace
list_files
List files and directories in a DBFS path
execute_sql
Execute a SQL statement
