apfel

MCP.Pizza Chef: Arthur-Ficial

Recent Macs ship with Apple Intelligence built in, but most tools ignore it and call a paid service instead. This exposes the on-device model as something your existing tools can talk to, using the same shape they already expect. So summarising, rewriting, and short questions can run locally with nothing sent anywhere and nothing to pay for. It needs a recent macOS with Apple Intelligence available.

Coding

Other

Writing

Use This MCP server To

Summarise text without sending it anywhere Rewrite a paragraph on my own machine Run short questions with no usage cost Point an existing tool at the local model Work offline without losing AI features

README

apfel

The free AI already on your Mac.

License: MIT

Apple Silicon Macs ship a built-in LLM via Apple FoundationModels. apfel exposes it as a UNIX tool and a local OpenAI-compatible server. 100% on-device. No API keys, no cloud.

Mode	Command	What you get
UNIX tool	`apfel "prompt"` / `echo "text" \| apfel`	Pipe-friendly answers, file attachments, JSON output, exit codes
OpenAI-compatible server	`apfel --serve`	Drop-in local `http://localhost:11434/v1` backend for OpenAI SDKs

apfel --chat - interactive REPL.

Tool calling works in all contexts. On-device context window: 4096 tokens on macOS 26, 8192 on macOS 27 - read at runtime, see Limitations.

apfel CLI

Requirements & Install

apfel FAQ

Can I use this without paying for an AI service?

Yes — it runs the model already on your Mac, so there is no usage cost.

Does my text leave my computer?

No, processing happens on-device, which is the main reason to use it.

What do I need for it to work?

A recent macOS with Apple Intelligence available on the machine.

Will my existing tools work with it?

It presents itself in the shape most tools already expect, so many can be pointed at it directly.

Is it as capable as a large cloud model?

No — an on-device model suits summarising and short tasks rather than the hardest reasoning work.