apple-mcp  by supermemoryai

Apple-native tool for model context protocol integration

created 5 months ago
2,253 stars

Top 20.5% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides a collection of Apple-native tools for interacting with the Model Context Protocol (MCP), enabling AI assistants like Claude Desktop and Cursor to leverage native macOS applications. It targets AI developers and power users seeking to integrate AI capabilities with their personal productivity workflows on Apple devices.

How It Works

The tools are built using Bun and leverage AppleScript and shell commands to interface with macOS applications such as Messages, Notes, Contacts, Mail, Reminders, Calendar, and Maps. This native approach allows for deep integration and control over these applications, facilitating complex workflows like composing and sending emails with attachments or scheduling reminders directly from an AI prompt.

Quick Start & Requirements

  • Installation: Via Smithery CLI: npx -y @smithery/cli@latest install @Dhravya/apple-mcp --client claude (or --client cursor).
  • Prerequisites: Bun (install via brew install oven-sh/bun/bun).
  • Setup: Configuration involves editing claude_desktop_config.json with the provided server details.
  • Demo: A setup and demo video is available at https://x.com/DhravyaShah/status/1892694077679763671.

Highlighted Details

  • Supports Messages, Notes, Contacts, Mail (including scheduling and attachments), Reminders, Calendar, and Web Search (DuckDuckGo).
  • Enables complex, chained commands for multi-step workflows (e.g., finding contacts and sending messages).
  • Provides functionality for searching, listing, creating, and managing data within native Apple applications.
  • Future TODOs include integration with Apple Photos and Apple Music.

Maintenance & Community

  • The project is maintained by Dhravya Shah.
  • No specific community links (Discord/Slack) or roadmap are provided in the README.

Licensing & Compatibility

  • The README does not explicitly state a license. The repository itself is under the MIT License.
  • Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is still under active development with "TODO" items for Photos and Music integration. The README does not detail error handling, performance benchmarks, or specific macOS version compatibility.

Health Check
Last commit

3 weeks ago

Responsiveness

1 day

Pull Requests (30d)
2
Issues (30d)
2
Star History
809 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.