Apple Reminders MCP Server
Enables management of Apple Reminders on macOS, including creating, updating, and querying reminders with due dates, priorities, and completion status across different reminder lists.
README
mcp-reminders
A Model Context Protocol (MCP) server for managing Apple Reminders.
Features
- Create, read, update, and delete reminders
- List reminder lists
- Mark reminders as complete
- Set due dates, priorities, and notes
- Query reminders by date range and completion status
Installation
uv sync
Usage
This server is designed to be used with Claude Desktop or other MCP clients.
Configuration
Add to your MCP settings:
{
"mcp-reminders": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-reminders",
"run",
"python",
"main.py"
]
}
}
Permissions
The first time you use this server, macOS will request permission to access your Reminders. Grant permission in:
System Settings > Privacy & Security > Reminders
Available Tools
list_reminder_lists()- List all reminder listslist_reminders(start_date?, end_date?, list_name?, include_completed?)- Query reminderscreate_reminder(CreateReminderRequest)- Create a new reminderupdate_reminder(reminder_id, UpdateReminderRequest)- Update an existing remindercomplete_reminder(reminder_id)- Mark a reminder as completeddelete_reminder(reminder_id)- Delete a reminder
Requirements
- macOS 10.14+
- Python 3.12+
- Access to Apple Reminders
TODO
Add Early Reminder Feature
Support for early reminders (notifications before due time) similar to macOS Reminders app UI.
What we've found:
- macOS Reminders UI has two separate fields: "Alarm" (due time) and "Early reminder" (notification before due time)
- EventKit's EKAlarm class supports both
relativeOffset(relative to due date) andabsoluteDate(specific time) alarms - There's a
isDefaultAlarmproperty that may distinguish between main alarm and early reminders - Early reminders set via macOS Reminders UI are not consistently readable via EventKit API - they may be stored differently than programmatically created alarms
- Current implementation creates reminders without alarms; users set
due_dateto their desired reminder time - Further investigation needed to properly read/write early reminders that match macOS Reminders app behavior
Add Reminder List Creation
Add ability to create new reminder lists (calendars) programmatically via create_reminder_list(name) function.
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。