
Notifications MCP Server
A Model Context Protocol server that allows AI agents to play notification sounds when tasks are completed.
README
✨ Notifications MCP Server ✨
Dream it, Pixel it. Made with ❤️ by Pink Pixel.
Overview
A Model Context Protocol server that allows AI agents to play a notification sound via a tool when a task is completed.
This is a TypeScript-based MCP server that provides a simple, configurable notification system. It demonstrates core MCP concepts by exposing a tool to play various sound alerts.
Features
Tools
play_notification
- Play a notification sound to indicate task completion.- Takes an optional
message
parameter to display with the notification. - Supports cross-platform sound playback (Windows and macOS).
- Takes an optional
Configuration
The notification sound can be configured using environment variables in your MCP client's configuration (e.g., MCP_config.json
).
You can choose from a set of downloadable sound files, or use your own MP3 file. You must configure the "MCP_NOTIFICATION_SOUND_PATH" environment variable to point to your desired sound file.
Available Sounds:
- cosmic_chime.mp3
- fairy_chime.mp3
- gentle_chime.mp3
- pleasant_chime.mp3
- retro_chime.mp3
You can download these sounds from the github repository - notification-mcp
Or alteratively, you can use your own MP3 file.
Whichever sound you choose, you must set the MCP_NOTIFICATION_SOUND_PATH
environment variable to the full path of the sound MP3 file, like so:
Example config.json
entry:
{
"mcpServers": {
"notifications": {
"command": "npx",
"args": ["-y", "@pinkpixel/notification-mcp"],
"env": {
"MCP_NOTIFICATION_SOUND_PATH": "C:\\Users\\YOUR_USERNAME\\path\\to\\your\\sound.mp3"
}
}
}
}
Important Note: Replace C:\\Users\\YOUR_USERNAME\\path\\to\\your\\sound.mp3
with the actual absolute path to your MP3 file. Ensure the path uses double backslashes \\
for Windows paths in JSON.
Usage
Once the server is configured and running, your MCP client can call the play_notification
tool.
Example Tool Call (from an AI agent or client SDK):
await client.request({
method: "tools/call",
params: {
name: "play_notification",
arguments: {
message: "Task completed successfully! 🎉"
}
}
});
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Installation
Run with npx:
{
"mcpServers": {
"notifications": {
"command": "npx",
"args": ["-y", "@pinkpixel/notification-mcp"]
"env": {
"MCP_NOTIFICATION_SOUND_PATH": "C:\\Users\\YOUR_USERNAME\\path\\to\\your\\sound.mp3"
}
}
}
}
Clone the Repository
{
"mcpServers": {
"notifications": {
"command": "node",
"args": ["\\path\\to\\notification-mcp\\build\\index.js"],
"env": {
"MCP_NOTIFICATION_SOUND_PATH": "C:\\Users\\YOUR_USERNAME\\path\\to\\your\\sound.mp3"
}
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
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。