mcpField
A
Apple Apps Mcp

Apple Apps Mcp

Local
github.com/0xatrillaProductivity4Updated 19w ago
Repository

About Apple Apps Mcp

Apple Apps Mcp is a local macOS app and MCP server that gives AI tools controlled access to Apple apps. A SwiftUI setup app manages permissions and client configuration, while safety checks cover selected higher-risk actions.

Key features

  1. 01SwiftUI setup app and permission status
  2. 02Calendar and Reminders access
  3. 03Notes, Mail, Music, and Shortcuts adapters
  4. 04Client setup helpers for Codex and Claude
  5. 05Confirmation safeguards for risky actions

Use cases

  1. 01List or create calendar events and reminders
  2. 02Search, read, or draft Apple Notes and Mail
  3. 03Search and control Music playback
  4. 04Run Shortcuts with confirmation

MCP support

The local stdio MCP server exposes tools for permissions, Calendar, Reminders, Notes, Mail, Music, and Shortcuts. Risky operations require `confirm: true` and a short `reason`.

#apple#mcp#icloud

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
AppIcon

Apple MCP

Apple MCP is a local macOS app and MCP server for giving AI tools controlled access to Apple apps.

It includes a SwiftUI setup app for permissions and client configuration, plus a TypeScript stdio MCP server for clients like Codex, Claude Code, Claude Desktop, Raycast, and any other MCP-compatible app.

Features

  • Native macOS setup app with integration toggles and permission status.
  • Calendar and Reminders access through EventKit.
  • Notes, Mail, Music, and Shortcuts adapters through local macOS automation surfaces.
  • Local MCP server over stdio.
  • Client setup helpers for Codex and Claude.
  • Safety guardrails for risky actions like sending mail, running shortcuts, and completing reminders.

MCP Tools

Apple MCP exposes these tools:

  • apple_permissions_status
  • apple_request_permission
  • calendar_list_events
  • calendar_create_event
  • reminders_list
  • reminders_create
  • reminders_complete
  • notes_search
  • notes_read
  • notes_create
  • mail_search
  • mail_read
  • mail_create_draft
  • mail_send_draft
  • shortcuts_list
  • shortcuts_run
  • music_search
  • music_play
  • music_pause

Risky tools require confirm: true and a short reason.

Download

Prebuilt releases are available on the Releases page.

The app is signed with a Developer ID certificate and notarized by Apple, so it opens normally with no Gatekeeper warnings — just drag Apple MCP to your Applications folder.

Requirements

  • macOS 26 or newer
  • Xcode command line tools / Swift toolchain
  • Node.js 20 or newer
  • npm

Build And Run

npm install
npm run build
swift build
./script/build_and_run.sh

The app stores local preferences at:

~/.apple-apps-mcp/config.json

Run The MCP Server

npm run dev:mcp

After building, you can register the server manually:

codex mcp add apple-apps -- node /absolute/path/to/dist/mcp/index.js
claude mcp add apple-apps -- node /absolute/path/to/dist/mcp/index.js

The setup app can also write or show client config for supported AI apps.

Permissions

Calendar and Reminders use native EventKit permissions. The setup app owns the foreground permission prompt and runs a localhost-only EventKit bridge so MCP calls share the approved app context.

Notes, Mail, Music, and Shortcuts may trigger macOS Automation prompts on first use.

Development

npm test
npm run build
swift build
./script/build_and_run.sh --verify

The Codex app Run button is wired through:

.codex/environments/environment.toml

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.