Skip to content

Conversation

@BlazStojanovic
Copy link
Contributor

Adding KumoRFM MCP server to the README.

Description

Motivation and Context

At kumo.ai we've built a foundation model for machine learning, which takes relational data (in the shape of several pandas dataframes) and makes in-context predictions. It allows users to predict/evaluate many machine learning queries without requiring training.

Since this workflow is particularly useful for agentic workflows, we have implemented the functionality as an MCP server for ease of integration.

model repo: https://github.com/kumo-ai/kumo-rfm
mcp repo: https://github.com/kumo-ai/kumo-rfm-mcp
docs: https://github.com/kumo-ai/kumo-rfm-mcp/blob/main/README.md

How Has This Been Tested?

The MCP client has been tested with several clients, including: Claude Desktop, Crew.ai, LangGraph, OpenAI agents SDK, Claude code SDK

Breaking Changes

No

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

Excited for our MCP server to be part of the official repo - happy to iron out any details to get this merged. TY in advance!

Co-authored-by: Matthias Fey <matthias.fey@tu-dortmund.de>
@domdomegg domdomegg merged commit 56bc00d into modelcontextprotocol:main Sep 12, 2025
19 checks passed
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.

3 participants