English Français العربية

apple-fm-mcp

Official registry AI and agents

Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package apple-fm-mcp
Claude Code 
claude mcp add apple-fm-mcp -- uvx apple-fm-mcp==1.0.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "apple-fm-mcp": {
            "command": "uvx",
            "args": [
                "apple-fm-mcp==1.0.1"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Apple Foundation Models MCP Server
  2. Requirements
  3. Install
  4. Configure
  5. Tools
  6. Why Use This?
  7. When to Use Apple FM vs Claude
  8. Built by Like One
  9. License

Apple Foundation Models MCP Server

Expose Apple's on-device 3B parameter LLM to Claude Code and Claude Desktop via MCP. Zero API cost, fully private, runs on Neural Engine.

Requirements

  • macOS 26+ (Tahoe or later)
  • Apple Silicon (M1/M2/M3/M4)
  • Apple Intelligence enabled in System Settings
  • Python 3.10+

Install

pip install apple-fm-mcp

Configure

Add to your Claude Code config (~/.claude/mcp.json):

{
  "mcpServers": {
    "apple-fm": {
      "command": "apple-fm-mcp"
    }
  }
}

Or Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "apple-fm": {
      "command": "apple-fm-mcp"
    }
  }
}

Tools

ToolDescriptionLatency
fm_generateFree-form text generation~1s
fm_summarizeSummarize text into bullet points~4s
fm_classifyClassify text into categories~2s
fm_extractExtract structured data from text~3s
fm_statusCheck model availabilityinstant

Why Use This?

  • Free: No API keys, no tokens, no cloud costs
  • Private: All inference on-device, no data leaves your Mac
  • Fast: Neural Engine optimized, ~1s for generation
  • Complementary: Use alongside Claude for tasks where on-device speed matters

When to Use Apple FM vs Claude

TaskUse Apple FMUse Claude
Quick classificationYesOverkill
Text summarizationYes (short text)Yes (long documents)
Code generationNoYes
Complex reasoningNoYes
Data extractionYes (simple)Yes (complex)
Privacy-criticalYesDepends

Built by Like One

AI education from a 501(c)(3) nonprofit. 50+ free courses on Claude, MCP, agents, and AI architecture.

License

MIT

Frequently asked questions

What is apple-fm-mcp?

Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence.

How do I install apple-fm-mcp?

It runs on your machine. In Claude Code: claude mcp add apple-fm-mcp -- uvx apple-fm-mcp==1.0.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does apple-fm-mcp need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is apple-fm-mcp open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains apple-fm-mcp?

It is published by sophiacave. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.