# colabfit-mcp

> Use this tool when you need to discover and utilize materials science datasets, train interatomic potentials, and validate models locally. It solves problems related to accessing and working with ColabFit datasets, and training MACE models, by providing a server for searching, downloading, training, and validation. The tool takes dataset queries and model parameters as inputs and outputs trained and validated MACE interatomic potentials.

Canonical page: https://skillsregistry.net/skills/colabfit-colabfit-mcp  
JSON: https://api.skillsregistry.net/v1/skills/colabfit-colabfit-mcp

## Description

An MCP server for discovering ColabFit materials science datasets and training MACE interatomic potentials on local hardware, enabling AI assistants to search, download, train, and validate models.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rhiqeq2xr9)
- **Repository:** <https://github.com/colabfit/colabfit-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "colabfit-colabfit-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/colabfit-colabfit-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/colabfit-colabfit-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt