Apple Reminders MCP Server
Enables AI assistants to manage Apple Reminders lists and reminders on macOS, including creating, updating, completing, and deleting reminders.
README
Apple Reminders MCP Server
A Model Context Protocol (MCP) server that allows AI assistants to interact with Apple Reminders on macOS using AppleScript.
Requirements
- macOS (required for AppleScript/Reminders integration)
- Node.js 18+
- Apple Reminders app with at least one list
- Automation permission (automatic prompt on first run)
Installation
# Clone the repository
git clone https://github.com/leawn/apple_reminders_mcp.git
cd apple_reminders_mcp
# Install dependencies and build
npm install
Usage with Cursor
Add to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"apple-reminders": {
"command": "/path/to/node",
"args": ["/path/to/apple_reminders_mcp/dist/index.js"]
}
}
}
Important: Use the full path to
node, not justnode. Find it withwhich node.Example for nvm users:
{ "mcpServers": { "apple-reminders": { "command": "/Users/yourname/.nvm/versions/node/v20.16.0/bin/node", "args": ["/Users/yourname/path/to/apple_reminders_mcp/dist/index.js"] } } }
Available Tools
| Tool | Description | Parameters |
|---|---|---|
listReminderLists |
Get all reminder lists | - |
getReminders |
Get reminders from a list | listName, includeCompleted? |
createReminder |
Create a new reminder | listName, title, notes?, dueDate?, priority? |
completeReminder |
Mark reminder as done | listName, reminderId |
uncompleteReminder |
Mark reminder as incomplete | listName, reminderId |
deleteReminder |
Delete a reminder | listName, reminderId |
updateReminder |
Update reminder details | listName, reminderId, title?, notes?, dueDate?, priority? |
Tool Parameters
Priority Values
0- No priority1- High priority5- Medium priority9- Low priority
Date Format
Dates should be in ISO8601 format:
2024-12-31T09:00:00Z
2024-12-31T09:00:00-05:00
CLI Reference
The shell script can be used directly for testing:
# List all reminder lists
./bin/reminders-helper.sh list-lists
# Get reminders from a list
./bin/reminders-helper.sh get-reminders --list "Work"
./bin/reminders-helper.sh get-reminders --list "Work" --include-completed
# Create a reminder
./bin/reminders-helper.sh create --list "Work" --title "New task"
./bin/reminders-helper.sh create --list "Work" --title "Meeting" --notes "Team sync" --due "2024-12-31T09:00:00Z" --priority 1
# Complete a reminder
./bin/reminders-helper.sh complete --list "Work" --id "x-apple-reminder://UUID"
# Uncomplete a reminder
./bin/reminders-helper.sh uncomplete --list "Work" --id "x-apple-reminder://UUID"
# Update a reminder
./bin/reminders-helper.sh update --list "Work" --id "x-apple-reminder://UUID" --title "Updated title"
# Delete a reminder
./bin/reminders-helper.sh delete --list "Work" --id "x-apple-reminder://UUID"
Permissions
On first run, macOS will prompt you to grant Automation permission for controlling the Reminders app. This uses the standard Automation permission (not the Reminders privacy permission), which is easier to grant and manage.
If you see permission errors:
- Open System Settings → Privacy & Security → Automation
- Find Terminal/Cursor and enable "Reminders"
Development
# Run TypeScript directly (without building)
npm run dev
# Build TypeScript
npm run build
# Start the server
npm start
Troubleshooting
"Not authorized to send Apple events"
- Open System Settings → Privacy & Security → Automation
- Find the app running the MCP server (Terminal, Cursor, etc.)
- Enable "Reminders" permission
- Restart the MCP server
"List 'X' not found"
Make sure the list name matches exactly (case-sensitive). Use listReminderLists to see available lists.
Commands are slow
The helper uses AppleScript with bulk property access, which should be fast. If commands are slow:
- Check if Reminders.app is responding
- Try quitting and reopening Reminders.app
- Restart the MCP server
License
MIT
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。