---
title: Equivariant Chem Scout
emoji: 🚀
colorFrom: purple
colorTo: green
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: mit
hf_oauth: true
tags:
  - mcp-in-action-track-creative

---

# Equivariant_Chem_Scout

An MCP server that teaches you how to build and train E(3)-equivariant Graph Neural Networks using the real MACE architecture.

## Features
- Initialize real MACE models with custom hyperparameters
- Train on molecular data with live Trackio logging
- Test equivariance properties interactively