$ loading_
Discover materials datasets and train and validate MACE potentials locally.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "colabfit-mcp" yet — see the docs or source repo.
Search ColabFit for datasets related to lithium-ion battery electrode materials. Organize them by element system, dataset size, and whether force and energy labels are included, then recommend the three best datasets for training a MACE potential.
A filtered dataset list, a comparison table of key attributes, and recommendations suited for training.
Download a ColabFit dataset suitable for the Al-O system, prepare the local training inputs, and provide the full commands, parameter recommendations, and directory structure for training a MACE potential.
Download steps, local training configuration, executable commands, and parameter guidance.
Design a validation workflow for my trained MACE potential, evaluate energy and force errors on a test set, and create an interpretation framework showing whether the model meets usability standards.
A validation workflow, evaluation metrics, result interpretation points, and criteria for judging usability.
Search open datasets across platforms and generate ready-to-run Colab starter code.
Connect to Colab so AI can run and manage cloud notebooks.
Access research workflows, retrieval tools, and knowledge resources for faster analysis.
Build, debug, and manage software tasks with natural language across LLMs.
Auto-generate MCP servers so AI can query data sources without code.
Search official library docs and return clean text ready for LLM use.