iMCP – Connect Your macOS Messages, Calendar, and More to Claude
Interact with all your Apple apps and data via Claude Desktop – or your favorite MCP client. MCPs are super hot right now but they're definitely still developer-grade user experiences. We built iMCP because we wanted to see what it would take to start to build a more consumer friendly experience on top of MCP. Not just connecting IDEs to databases and SaaS APIs. iMCP is open source and built entirely in Swift with our MCP Swift implementation: https://github.com/loopwork-ai/mcp-swift-sdk Tell us what you think!
In plain words
iMCP is an open-source tool that connects Apple's Messages, Calendar, and other macOS apps to Claude Desktop or other MCP clients, allowing users to interact with their Apple data through AI. Built entirely in Swift, it aims to make Model Context Protocol technology more accessible to everyday users rather than just developers. The tool integrates personal productivity apps with AI assistants in a consumer-friendly way.
written from the facts on this page · September 2026
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
