mcp-databricks
Provides tools for interacting with Databricks SQL and metadata, including table discovery, column alterations, and DDL operations.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-databricksshow me the tables in the default schema"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
File Structure
mcp-databricks/
├── .env # Environment variables (DATABRICKS_HOST, TOKEN, etc.)
├── Dockerfile # Containerization for deployment
├── README.md
├── pyproject.toml # or requirement.txt
└── src/
├── __init__.py
├── server.py # Server entrypoint, initializes MCP server and registers tools
├── config.py # Configuration management using Pydantic Settings
├── db/
│ ├── __init__.py
│ ├── client.py # Databricks SQL connection pool / Databricks SDK client
│ └── operations.py # Low-level SQL execution & metadata query logic
├── models/
│ ├── __init__.py
│ ├── metadata.py # Pydantic models for Table/Column schemas and discovery
│ └── operations.py # Pydantic models for Alter/Write request payloads
└── tools/
├── __init__.py
├── metadata.py # MCP tools for reading tables and discovery
└── warehouse.py # MCP tools for altering columns and DDL operations
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yabur/mcp-databricks'
If you have feedback or need assistance with the MCP directory API, please join our Discord server