Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Unity Catalog MCP server #683

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

ognis1205
Copy link

@ognis1205 ognis1205 commented Feb 26, 2025

Description

An MCP server that enables LLMs to interact with Unity Catalog AI, supporting CRUD operations on Unity Catalog Functions and executing them as MCP tools.

Server Details

Server: https://github.com/ognis1205/mcp-server-unitycatalog
MCP to interact with Unity Catalog AI - https://docs.unitycatalog.io/#unity-catalog-open-multimodal-catalog-for-data-ai

Motivation and Context

  • Added MCP tools for list_functions, get_function, create_python_function, execute_function, and delete_function in Unity Catalog AI.
  • Python UDFs added to Unity Catalog are now available as MCP tools.
  • Tools updated via CRUD operations are instantly reflected on the client through server notifications.

With this update, you can seamlessly generate Python code in Cline, add it to Unity Catalog, and execute it as an MCP tool—all in a single workflow. It’s all about boosting your development efficiency.

How Has This Been Tested?

  • Tested using an MCP-compatible client, e.g., VSCode/Cline and Claude Desktop
  • Verified that all tools return expected responses from Unity Catalog AI API.

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation update

Checklist

  • I have read the MCP Protocol Documentation
  • My changes follows MCP security best practices
  • I have updated the server's README accordingly
  • I have tested this with an LLM client
  • My code follows the repository's style guidelines
  • New and existing tests pass locally
  • I have added appropriate error handling
  • I have documented all environment variables and configuration options

Additional context

Signed-off-by: Shingo OKAWA <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant