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.
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.
The 'every connection requires approval and can be revoked' line is what matters most to me here, but how granular is that approval? Is it per-app (grant Calendar but withhold Messages/Mail), or one grant per client that then covers everything Macuse can touch? And for outbound actions like sending a Message or letting a Mail draft actually go out, is that gated separately each time, or does the initial connection approval cover silent sends?
finally something that lets me ask claude to pull events from my calendar without weird workarounds, super clean mac feel too
Finally a clean way to let Claude actually touch my Mac apps without weird workarounds. Setup with Calendar and Mail took like two minutes and the permissions prompt felt transparent instead of sketchy.
How does Macuse handle permissions when giving an AI client access to Mail and Messages, and is there any sandboxing or audit log so I can see exactly what got read or sent?
Finally a clean way to let Claude actually read my Mail and Calendar without weird workarounds. The MCP setup was painless and everything stayed local.
Finally something that lets Claude actually touch my Mac apps without me copy-pasting between windows. Calendar and Mail worked right away once I granted the permissions, and the MCP setup was painless.
Does Computer Use actually click around in your real apps without sandbox issues, or do you need to grant a bunch of accessibility permissions first?
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
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
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!
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?
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?
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.
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.
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?
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.
About Macuse on Product Hunt
“Give Your AI Superpowers on macOS”
Macuse launched on Product Hunt on July 2nd, 2026 and earned 119 upvotes and 24 comments, placing #11 on the daily leaderboard. 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.
Macuse was featured in Mac (103.6k followers), Productivity (655.6k followers) and Artificial Intelligence (473.1k followers) on Product Hunt. Together, these topics include over 258.8k products, making this a competitive space to launch in.
Who hunted Macuse?
Macuse was hunted by Yuexun Jiang. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Macuse stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Yuexun Jiang
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.