Provides tools for interacting with Databricks, enabling cluster management, job management, notebook management, DBFS management, and SQL management within a Databricks environment.
Databricks MCP Server
This is a server that provides tools to interact with Databricks.
Features
Cluster management
Job management
Notebook management
DBFS management
SQL management
Related MCP server: MCP-Python
Installation
Required Python version: 3.11
Configuration
The server can be configured using environment variables or a .env file.
Environment variables
DATABRICKS_HOST: The Databricks host URL (e.g. https://adb-123456789012345.12.azuredatabricks.net)DATABRICKS_TOKEN: The Databricks API tokenTRANSPORT: The transport to use (e.g. sse). Options: [stdio, sse, streamable-http]. Default: sseSERVER_HOST: The host to bind the server to (e.g. 0.0.0.0)SERVER_PORT: The port to bind the server to (e.g. 8000)DEBUG: Whether to run the server in debug mode (e.g. True)LOG_LEVEL: The log level (e.g. INFO)
.env file
Create a .env file in the root directory of the project with the following variables:
Obtaining Databricks Credentials
Host: Your Databricks instance URL (e.g., your-instance.cloud.databricks.com)
Token: Create a personal access token in Databricks:
Go to User Settings (click your username in the top right)
Select "Developer" tab
Click "Manage" under "Access tokens"
Generate a new token, and save it (it will not be shown again)
Running the server in standalone mode
Config Claude-Desktop/Cursor/Windsurf
Add the following to your Claude-Desktop/Cursor config file:
If you are using Claude-Desktop, restart it for the changes to take effect.