truth0530 GitHub avatar

mcp-server-ios-shortcuts

truth0530

A zero-dependency Python MCP server for macOS that exposes tools for AI agents to build, sign, import, list, inspect, run, and share iOS/macOS Shortcuts using Apple's shortcuts CLI.

Stars

6

7-day growth

No data

Forks

0

Open issues

0

License

MIT

Last updated

2026-07-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It turns natural-language agent intent into signed .shortcut binaries while supporting many MCP clients, and it includes a v2 toolchain with decompilation, recipe validation, magic variables, templates, and an honest action-coverage system.

Who it is for

  • macOS users who use AI coding agents such as Grok, Codex, Claude, Cursor, or Gemini
  • Shortcuts power users who want to create or maintain shortcuts programmatically or via natural language
  • Developers building MCP-based automation tooling around Apple Shortcuts

Use cases

  • Have an AI agent build, sign, and import a shortcut from a natural-language request
  • Decompile an existing .shortcut into editable JSON to modify or clone it
  • Generate ready-made shortcuts from built-in templates such as screenshot OCR, clipboard notification, or HTTP GET
  • List, inspect, run, or open installed shortcuts without leaving an MCP client

Strengths

  • Runs on Python 3.8+ with only the standard library, so there is no pip install or Node dependency
  • Provides a broad tool set covering action lookup, recipe validation, decompilation, building, signing, importing, inspecting, and running shortcuts
  • Includes safety mechanisms such as write-path sandboxing, SAFE_MODE for dangerous actions, and send_imessage never auto-sending
  • Ships ready-made configuration snippets for Grok, Codex CLI, Claude Desktop/Code, Cursor, and Gemini/Antigravity

Considerations

  • Requires macOS Monterey or later and the system shortcuts CLI; it is not cross-platform
  • The generic action path uses auto-coercion rather than full Apple schema parity, so some actions may need manual validation or raw WF escape hatches
  • Some learning features require Full Disk Access, and safe mode intentionally blocks run_shortcut and send_imessage

README quick start

Quick start

Related repositories

Similar projects matched by category, topics, and programming language.

Blaizzy
Featured
Blaizzy GitHub avatar

nativ

Nativ is a native macOS app that lets you run AI models locally on Apple silicon, offering chat, model management, performance analytics, and an OpenAI/Anthropic-compatible API server.

AI & Machine LearningAI Vision & Audio
985
makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941