Macuse
Give Your AI Superpowers on macOS
Start new thread

Macuse - Give Your AI Superpowers on macOS

by•
Macuse is a native macOS app that connects Claude, Codex, Cursor, Raycast, and any MCP-compatible AI client to your Mac apps. It gives AI assistants local access to Calendar, Mail, Notes, Reminders, Messages, and real app control through Computer Use.

Add a comment

Replies

Best
Maker
📌

Hey Product Hunt,

I built Macuse because AI assistants are getting incredibly good at reasoning, but on macOS they still often hit a wall: they can answer questions, but they cannot reliably act across the apps where your work actually lives.

Macuse is a native macOS app that turns your Mac apps into local tools for AI assistants.

It runs as a local MCP server, connecting Claude, Codex, Cursor, Raycast, and any MCP-compatible client to your Mac. Your AI can manage Calendar events, read and draft Mail, work with Notes and Reminders, search Contacts, send Messages, and use Computer Use to click, type, scroll, and navigate real app interfaces.

A few things I cared about while building it:

• Local-first: your Mac app data is processed locally
• Permissioned: every connection requires approval and can be revoked
• Multi-client: one Macuse setup works across your AI tools
• Native integrations: Calendar, Mail, Notes, Reminders, Messages, Contacts, Shortcuts, Maps, and more
• Computer Use: control apps that do not have APIs, without taking over your active cursor/window

The goal is simple: make your AI assistant useful inside the Mac apps you already use every day.

I’d love feedback from Mac users, MCP builders, and anyone experimenting with AI agents on desktop workflows.

Love how it stays truly native on macOS instead of wrapping everything in an Electron shell. Tying Calendar, Mail, and Notes together through one MCP layer is the kind of plumbing I have been waiting for.

Maker

 Thanks Hilal!

Native-first and a single MCP layer across your apps were exactly the goal. Give it a try and let me know what’s missing!

This looks great for the AI can reason but can't reach my apps problem. One thing I'm curious about: when Computer Use is driving clicks and typing in an app without an API, how do you handle it if it clicks the wrong thing in Mail or Messages before you can stop it? Is there some kind of review or undo step, or does it just fire at full speed once permission is granted?

Maker
Great question. For Computer Use, Macuse asks for permission for each individual app before operating it. So even after Accessibility is enabled at the macOS level, an AI client cannot just start controlling any app silently. The user stays in control of which apps Computer Use is allowed to access.

connecting MCP clients to native mac apps is the missing layer for local workflows. right now claude can browse the web and run code but can't touch the calendar sitting right there on the same machine. the messages and mail access is where it gets interesting and also where it gets risky. what does the permission model look like? per-app grants, per-action approval, or one big trust decision at install? that choice basically determines whether people feel safe using it for anything real.

Maker
Totally agree， the permission model is the key part. Macuse is not a one-time “trust everything” install. It relies on macOS permissions, explicit AI client approval, and revocable access. You can choose what to enable, and I’m continuing to make the controls more granular, especially for sensitive apps like Mail and Messages.

Hi Yuexun, the reassuring part for me is that it stays helpful without ever feeling like it might run off and do something behind my back. That sense of staying in the driver's seat matters a lot to me.

Maker
Thank you, that’s exactly the goal. Macuse should make AI more useful inside your Mac apps, but still keep you in control through local access, explicit client approval, and revocable permissions.

How does it actually handle permissions when an AI wants to send a message or move a calendar event, do you get a prompt each time or is there a way to set trusted rules upfront?

Maker
Good question. Macuse is not a one-time “trust everything” setup. Native app access is gated by macOS permissions and approved AI client connections, and access can be revoked anytime. For sensitive actions like sending messages or changing calendar events, I’m working on more explicit confirmation controls so users can decide what should require approval.

How does it handle permissions when it needs to actually click around in apps via Computer Use, especially for things that need accessibility access every launch?

Maker
Accessibility is granted once through macOS System Settings, not every launch. But for Computer Use, Macuse still asks for permission for each individual app before operating it, so enabling Accessibility does not mean an AI client can control every app automatically.

Hello yuexunjiang, I like the design a lot, it looks elegant. I have a quick question. What about the privacy issue? This AI agent will have access to all my emails, messages, reminders, prompts from my macOS apps? Congrats on the launch, let's connect!


Maker
Thank you! Privacy is a core part of Macuse. Macuse runs locally on your Mac and acts as a bridge between your AI client and your Mac apps. It does not store your emails, messages, or reminders on a server. If you use a cloud AI client, the data needed for your request may be sent to that provider, so the final privacy boundary also depends on the AI client/model you choose.

the fact that it sits natively in the menu bar and just hands AI tools straight access to calendar and mail without weird workarounds is genuinely thoughtful engineering

mcp calls and computer-use have very different blast radii — reading a calendar is a scopable tool call, but 'real app control' via computer use is an unscoped click that does whatever the frontmost app can. the gate between those two is the hard part

12
Next