# fm-mcp

> fm-mcp — yrangana-fm-mcp. Use this tool when you need to offload simple text tasks to an on-device model, freeing up resources for more complex tasks, and integrate with Apple Foundation Models using a single Rust binary. It solves problems of resource allocation and efficiency in text processing workflows. Ideal for use cases where local processing is preferred, such as data preprocessing or automation tasks, with input and output capabilities via git integration.

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

## Description

Let Claude Code and Codex delegate simple text work to the on-device model for Apple Foundation Models. One Rust binary.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-10-26

## Source

- **Source listing:** [GitHub](https://github.com/yrangana/fm-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": "yrangana-fm-mcp"
    }
  }
}
```

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