Databricks Genie MCP
This project implements a Model Context Protocol (MCP) server, exposing the Databricks Genie API functionality as a tool. It supports querying Databricks data in natural language and can be integrated with MCP clients such as Claude Desktop.
rating : 2 points
downloads : 9.4K
What is the Databricks Genie MCP service?
This service transforms the Genie AI assistant functionality of Databricks into a standardized MCP tool, allowing you to interact with AI assistants like Claude in natural language to query information in the Databricks data warehouse. You can obtain data insights in everyday language without writing SQL.How to use the Genie MCP service?
Simply configure the service path in clients that support the MCP protocol, such as Claude Desktop, and you can query data through conversations. For example, ask 'How much were our DBU consumption last month?' and the system will automatically convert it into an SQL query and return the results.Use cases
It is suitable for scenarios where business personnel need to quickly obtain data insights, monitor system usage, audit data access records, etc., and do not want to write SQL for frequent queries. It is particularly suitable for ad - hoc data exploration and analysis needs.Main features
Natural language query
You can obtain data by asking questions in everyday English or Chinese without learning SQL syntax.
Conversation management
Supports creating and managing multi - turn conversation contexts to maintain query coherence.
Intelligent SQL generation
Automatically converts natural language into optimized SQL queries.
Result retrieval
Supports retrieving complete query results or summary reports.
Advantages
Zero - code data analysis, reducing the technical threshold
Real - time connection to the Databricks data warehouse, with accurate and reliable results
Supports progressive clarification of complex queries and multi - turn conversations
Integrated with the enterprise - level security system, with fine - grained permission control
Limitations
Databricks workspace administrators need to pre - configure access permissions
Professional data teams may still need to be involved in complex analyses
Query performance is limited by Genie and SQL warehouse resources
How to use
Environment preparation
Ensure that Python 3.10+ and the Databricks CLI are installed, and obtain workspace access permissions.
Configure authentication
Create a.env file in the working directory to set Databricks authentication information.
Client configuration
Add the MCP server configuration in the Claude Desktop settings, specifying the Python interpreter and script path.
Start querying
Use the tool icon in the Claude chat window to select the Genie function or ask questions in natural language.
Usage examples
Resource usage monitoring
Business managers want to know the team's resource consumption.
Data security audit
The security team checks sensitive data access records.
Frequently Asked Questions
Why can't Claude Desktop find the Genie tool?
What should I do if the query returns a permission error?
How to improve the query response speed?
Related resources
Genie MCP technical blog
Detailed technical implementation principles and use - case analyses.
Claude Desktop download
Official MCP client application.
MCP protocol specification
Technical standard document for the Model Context Protocol.

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
16.6K
4.3 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
14.8K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
24.5K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
44.7K
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
20.2K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
44.3K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
30.2K
4.8 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
14.8K
4.5 points