Apple Reminders MCP Server
MCP server enabling AI assistants to create, read, list, and delete Apple Reminders on macOS via AppleScript.
README
Apple Reminders MCP Server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Apple Reminders on macOS. This server provides tools to create, read, list, and delete reminders programmatically through AppleScript.
Features
- ✅ Create reminders with due dates, times, notes, and locations
- 📋 List all reminder lists
- 🔍 Fetch reminders from specific lists (completed or pending)
- 🗑️ Delete reminders by name
- 🤖 Compatible with Claude Desktop and other MCP clients
- 🍎 Native macOS integration via AppleScript
- 🔒 Input sanitization to prevent AppleScript injection
Demo
https://github.com/user-attachments/assets/d36e0df3-ff4b-4f48-bb29-41ddb5483c6b
Prerequisites
- macOS (required for AppleScript)
- Python 3.10 or higher
- Apple Reminders app
Installation
Option 1: Install from PyPI (Recommended)
pip install apple-reminders-mcp
Option 2: Install from source
git clone https://github.com/shreyanshjain05/apple_reminder_mcp_server.git
cd apple_reminder_mcp_server
pip install -e .
Usage
Running the Server
If installed via pip:
apple-reminders-mcp
Or run directly:
python -m apple_reminders_mcp.server
Testing with MCP Inspector
npx @modelcontextprotocol/inspector python3 server.py
This will:
- Start a proxy server on
localhost:6277 - Open the inspector interface in your browser at
http://localhost:6274 - Display a session token for authentication
Integration with Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"apple-reminders": {
"command": "python3",
"args": ["/path/to/apple_reminder_mcp_server/server.py"]
}
}
}
Note: Replace
/path/to/with the actual path where you cloned the repo. If you get "Server disconnected" errors, use the full path to your Python executable (runwhich python3to find it).
Available Tools
1. create_reminder
Creates a new reminder in Apple Reminders.
Parameters:
title(required): The title of the reminderdue_date(required): Due date (e.g., "2024-12-25", "tomorrow", "next Friday")due_time(optional): Time in HHMMSS format (default: 090000 for 9 AM)notes(optional): Additional notes/body textlist_name(optional): Target list name (default: "Reminder Created using Agent")location(optional): Location for location-based reminders
Example:
{
"title": "Team Meeting",
"due_date": "tomorrow",
"due_time": "140000",
"notes": "Discuss Q1 goals",
"list_name": "Work"
}
2. get_reminder
Fetches reminders from a specific list.
Parameters:
list_name(required): Name of the reminder listcompleted(optional): Whether to fetch completed reminders (default: false)limit(optional): Maximum number of reminders to return (default: 20)
3. list_reminder_lists
Returns all available reminder lists. No parameters required.
4. delete_reminder
Deletes a reminder by name.
Parameters:
name(required): The exact name of the reminder to deletelist_name(optional): Specific list to search in (searches all lists if not provided)
Troubleshooting
Common Issues
-
Permission errors with AppleScript
- Grant Terminal/IDE permission to control Reminders in System Preferences → Security & Privacy → Automation
-
"No reminder list found" error
- Make sure the list name exactly matches (case-sensitive)
- Use
list_reminder_liststo see available lists
-
Date parsing errors
- Use standard formats like "YYYY-MM-DD" or natural language like "tomorrow"
Development
Running Tests
pip install -e ".[dev]"
pytest tests/ -v
Project Structure
apple_reminder_mcp_server/
├── .github/workflows/
│ ├── test.yml # CI testing
│ └── publish.yml # PyPI publishing
│── __init__.py
├── pyproject.toml # Package configuration
├── server.py # Main MCP server implementation
└── README.md
├── tests/
│ ├── __init__.py
│ └── test_server.py # Unit tests
Contributing
See CONTRIBUTING.md for guidelines.
License
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
Acknowledgments
- Built with FastMCP
- Uses AppleScript for native macOS integration
- Compatible with the Model Context Protocol
<p align="center"> <br><br> ⭐ Star this repo if you find it useful! <br><br> ☕ You can also support me on Ko-fi: https://ko-fi.com/shreyanshjain05 — every coffee keeps me going! </p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。