
Python Apple MCP
A Python server that enables interaction with macOS native applications (Contacts, Notes, Mail, Messages, Reminders, Calendar, and Maps) through AppleScript, featuring asynchronous operations and type-safe interfaces.
README
Python Apple MCP (Model Context Protocol)
A Python implementation of the server that handles interactions with macOS applications such as Contacts, Notes, Mail, Messages, Reminders, Calendar, and Maps using FastMCP.
Features
- Interact with macOS native applications through AppleScript
- Asynchronous operations for better performance
- Comprehensive error handling
- Type-safe interfaces using Pydantic models
- Extensive test coverage
- Modular design for easy extension
Supported Applications
- Contacts
- Notes
- Messages
- Reminders
- Calendar
- Maps
Installation
- Clone the repository:
git clone https://github.com/jxnl/python-apple-mcp.git
cd python-apple-mcp
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Install test dependencies (optional):
pip install -r requirements-test.txt
Usage
Basic Example
from apple_mcp import FastMCP, Context
# Initialize FastMCP server
mcp = FastMCP("Apple MCP")
# Use the tools
@mcp.tool()
def find_contact(name: str) -> List[Contact]:
"""Search for contacts by name"""
# Implementation here
pass
# Run the server
if __name__ == "__main__":
mcp.run()
Using Individual Modules
from utils.contacts import ContactsModule
from utils.notes import NotesModule
# Initialize modules
contacts = ContactsModule()
notes = NotesModule()
# Use the modules
async def main():
# Find a contact
contact = await contacts.find_contact("John")
# Create a note
await notes.create_note(
title="Meeting Notes",
body="Discussion points...",
folder_name="Work"
)
# Run the async code
import asyncio
asyncio.run(main())
Testing
Run the test suite:
pytest
Run tests with coverage:
pytest --cov=utils tests/
Run specific test file:
pytest tests/test_contacts.py
API Documentation
Contacts Module
find_contact(name: str) -> List[Contact]
: Search for contacts by nameget_all_contacts() -> List[Contact]
: Get all contactscreate_contact(name: str, phones: List[str]) -> Contact
: Create a new contact
Notes Module
find_note(query: str) -> List[Note]
: Search for notescreate_note(title: str, body: str, folder_name: str) -> Note
: Create a new noteget_all_notes() -> List[Note]
: Get all notes
Mail Module
send_email(to: str, subject: str, body: str) -> str
: Send an emailsearch_emails(query: str) -> List[Email]
: Search emailsget_unread_mails() -> List[Email]
: Get unread emails
Messages Module
send_message(to: str, content: str) -> bool
: Send an iMessageread_messages(phone_number: str) -> List[Message]
: Read messagesschedule_message(to: str, content: str, scheduled_time: str) -> Dict
: Schedule a message
Reminders Module
create_reminder(name: str, list_name: str, notes: str, due_date: str) -> Dict
: Create a remindersearch_reminders(query: str) -> List[Dict]
: Search remindersget_all_reminders() -> List[Dict]
: Get all reminders
Calendar Module
create_event(title: str, start_date: str, end_date: str, location: str, notes: str) -> Dict
: Create an eventsearch_events(query: str) -> List[Dict]
: Search eventsget_events() -> List[Dict]
: Get all events
Maps Module
search_locations(query: str) -> List[Location]
: Search for locationsget_directions(from_address: str, to_address: str, transport_type: str) -> str
: Get directionssave_location(name: str, address: str) -> Dict
: Save a location to favorites
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.