MCPing
Enables AI assistants to send desktop notifications on macOS with rich formatting, urgency levels, and sound options.
README
MCPing - macOS Notification MCP Server
I got a notification! 🎉
MCPing is a Model Context Protocol (MCP) server that enables AI assistants to send desktop notifications on macOS. Finally, your AI can tap you on the shoulder instead of just sitting there quietly being brilliant.
Installation
Prerequisites: Node.js 18+ and macOS (for notifications)
Quick Start (Recommended)
Add to your MCP client settings:
{
"mcpServers": {
"toolprint-mcping": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@toolprint/mcping-mcp@latest"]
}
}
}
Manual Installation
npm install -g @toolprint/mcping-mcp@latest
mcping-mcp
Configuration
For Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcping": {
"command": "npx",
"args": ["-y", "@toolprint/mcping-mcp@latest"]
}
}
}
For Development (HTTP Mode)
# Run in HTTP mode for testing
npx @toolprint/mcping-mcp@latest --transport http --port 3000
# Test with curl
curl -X POST http://localhost:3000/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "send-notification",
"arguments": {
"title": "Hello World",
"message": "This is a test notification"
}
}
}'
Usage
Once configured, ask your AI assistant:
- "Send a notification saying the build is complete"
- "Send a critical alert that the server is down"
- "Send a quiet reminder to take a break"
- "Notify me with title 'Tests Passed' and message 'All 127 tests passed'"
Tool: send-notification
Send desktop notifications on macOS with rich formatting options.
Parameters:
title(required): Notification title (1-100 characters)message(required): Notification message (1-500 characters)subtitle(optional): Additional context (max 100 characters)urgency(optional):"low"|"normal"|"critical"(default:"normal")sound(optional): Play notification sound (default:true)timeout(optional): Display duration in seconds, 1-60 (default: 10)
Examples:
// Basic notification
{
"title": "Task Complete",
"message": "Your build finished successfully"
}
// Critical alert with subtitle
{
"title": "Server Down",
"message": "Production server is not responding",
"subtitle": "api.example.com",
"urgency": "critical",
"sound": true,
"timeout": 60
}
// Quiet reminder
{
"title": "Break Time",
"message": "You've been coding for 2 hours",
"urgency": "low",
"sound": false,
"timeout": 10
}
Troubleshooting
Notifications Not Appearing?
- Check Permissions: System Preferences → Notifications → Terminal (allow notifications)
- Do Not Disturb: Ensure DND is disabled or use
urgency: "critical" - Verbose Mode: Run with
--verboseflag for detailed logs
Common Issues
- "Permission denied": Grant Terminal notification permissions in System Preferences
- "Not available": Ensure you're running on macOS
- "Rate limited": Wait between sending multiple notifications
Development
# Clone repository
git clone https://github.com/toolprint/mcping-mcp.git
cd mcping-mcp
# Install dependencies
npm install
# Run tests
npm test
# Build
npm run build
# Development mode
npm run dev
License
MIT © Toolprint
Usage
When using, forking, or distributing this software, the MIT License requires that you include the original copyright notice ("Copyright © OneGrep, Inc.") and license text in all copies or substantial portions of the software. This attribution requirement ensures proper credit to the original authors while allowing you to freely use, modify, and distribute the code.
About Toolprint
Building tools for the AI agent ecosystem. Visit toolprint.ai to explore our suite of MCP servers and developer tools.
<div align="center"> <strong>MCPing</strong> - Desktop notifications for AI assistants<br> Made with ❤️ by <a href="https://toolprint.ai">Toolprint</a> </div>
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。