PyApple MCP Tools
Python tools for MCP that integrate with native Apple applications like Messages, Notes, Mail, and more on macOS.
PyApple MCP Tools
A Python implementation of Apple-native tools for the Model Context Protocol (MCP), providing seamless integration with macOS applications.
Features
- Messages: Send and read messages using the Apple Messages app
- Notes: List, search, create, and delete notes in Apple Notes app
- Contacts: Search contacts from Apple Contacts
- Emails: Send emails, search messages, and manage mail with Apple Mail
- Reminders: List, search, and create reminders in Apple Reminders app
- Calendar: Search events, create calendar entries, and manage your schedule
- Web Search: Search the web using DuckDuckGo
- Maps: Search locations, get directions, and manage guides with Apple Maps
Quick Installation
Automated Setup (Recommended)
# Install pyapple-mcp
pip install pyapple-mcp
# Run the setup helper to configure Claude Desktop
pyapple-mcp-setup
The setup helper will:
- Find your pyapple-mcp installation
- Locate your Claude Desktop config file
- Automatically add the configuration
- Display helpful setup information
Manual Installation
-
Install pyapple-mcp:
pip install pyapple-mcp -
Configure Claude Desktop by editing
~/Library/Application Support/Claude Desktop/claude_desktop_config.json:{ "mcpServers": { "pyapple": { "command": "pyapple-mcp" } } } -
Restart Claude Desktop to load the new configuration.
Usage Examples
Basic Commands
Can you send a message to John Doe saying "Hello from Claude!"?
Find all notes about "AI research" and summarize them
Create a reminder to "Buy groceries" for tomorrow at 5pm
Search my calendar for events this week containing "meeting"
Get directions from "Apple Park" to "San Francisco Airport"
Advanced Workflows
You can chain commands together for complex workflows:
"Read my note about the conference attendees, find their contact information, and send them a thank you email"
Development
Local Setup
-
Clone the repository:
git clone https://github.com/pyapple-mcp/pyapple-mcp.git cd pyapple-mcp -
Install dependencies:
pip install -e ".[dev]" -
Run the development server:
python -m pyapple_mcp.server
Testing with MCP Inspector
# Test the server
mcp dev pyapple_mcp/server.py
# Test with dependencies
mcp dev pyapple_mcp/server.py --with httpx --with beautifulsoup4
Requirements
- macOS 10.15+ (Catalina or later)
- Python 3.10+
- Appropriate permissions for accessing:
- Contacts
- Calendar
- Messages
- Notes
- Reminders
- Automation (for controlling apps)
Permissions Setup
On first use, macOS will prompt for various permissions. Grant access to:
- Contacts - for contact search functionality
- Calendar - for calendar event management
- Messages - for sending/reading messages
- Mail - for email operations
- Notes - for notes access
- Reminders - for reminder management
- Automation - for controlling applications via AppleScript
Troubleshooting
Common Issues
Permission Denied Errors:
- Go to System Settings > Privacy & Security
- Grant access to the required applications
- Restart Claude Desktop
Module Import Errors:
- Ensure you're running on macOS
- Install PyObjC frameworks:
pip install pyobjc
AppleScript Execution Errors:
- Check that the target applications are installed
- Verify automation permissions in System Settings
Setup Issues:
- Run
pyapple-mcp-setup --helpfor setup options - Check that pyapple-mcp is in your PATH:
which pyapple-mcp - Use
pyapple-mcp-setup --config-path /path/to/configfor custom config locations
Debug Mode
Run with debug logging:
PYAPPLE_DEBUG=1 python -m pyapple_mcp.server
Architecture
pyapple-mcp/
├── pyapple_mcp/
│ ├── __init__.py
│ ├── server.py # Main MCP server
│ ├── setup_helper.py # Setup and configuration helper
│ └── utils/
│ ├── __init__.py
│ ├── applescript.py # AppleScript execution
│ ├── calendar.py # Calendar integration
│ ├── contacts.py # Contacts integration
│ ├── mail.py # Mail integration
│ ├── maps.py # Maps integration
│ ├── messages.py # Messages integration
│ ├── notes.py # Notes integration
│ ├── reminders.py # Reminders integration
│ └── websearch.py # Web search functionality
├── tests/
├── requirements.txt
├── README.md
├── LICENSE
└── pyproject.toml
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes
- Run tests:
pytest - Submit a pull request
License
MIT License - see LICENSE file for details.
Acknowledgments
- Inspired by the original apple-mcp TypeScript implementation
- Built with the MCP Python SDK
- Uses PyObjC for macOS system integration
Related Servers
Kone.vc
sponsorMonetize your AI agent with contextual product recommendations
Freshdesk
Integrates with Freshdesk to manage support tickets, contacts, and other customer service operations.
Sheet-Cello
A specialized Google Sheets integration server that allows the LLM to read, write, and manage spreadsheet data in real-time. This server supports cell-level manipulation, bulk range updates, and full worksheet retrieval, enabling the model to perform data analysis, logging, and automated reporting directly within Google Worksheets.If you have functions which take range value then first read the sheet and decide where user is asking to add data and define range by your own.Provides 46 tools for Gsheet
Umbraco MCP
Interact with the Umbraco CMS Management API for administrative tasks.
Great Question
Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.
Unchained Engine
E-Commerce Engine with built-in MCP Server
Vedit-MCP
Perform basic video editing operations using natural language commands. Requires ffmpeg to be installed.
ONLYOFFICE DocSpace
Interact with ONLYOFFICE DocSpace for document collaboration and management.
CV Forge MCP
Forge powerful, ATS-friendly CVs tailored to any job - an MCP server for intelligent CV generation
Mindmap MCP Server
Convert Markdown content into interactive mindmaps.
Open-Brain
MCP memory server that builds a knowledge graph as you capture thoughts. 16 tools. Self-hostable.