What are the runtime requirements?
Requires Python 3.8 or higher. On Windows, the win10toast library is needed; on macOS, osascript is built-in.
@naru-sensei
Basic information
A Model Context Protocol (MCP) server with Windows 10 desktop notifications support. It processes notification requests from MCP clients like VSCode Cline and displays customizable desktop notifications using win10toast.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"-toast-mcp-server": {
"command": "python",
"args": [
"mcp_server.py",
"--port",
"8000",
"--host",
"0.0.0.0"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Windows 10 および macOS 通知機能付き MCP サーバー is a Model Context Protocol (MCP) server that displays desktop notifications on Windows 10 (using win10toast) and macOS (using osascript). It accepts requests from MCP clients such as VSCode Cline and triggers notifications based on those requests.
Run the server with Python 3.8 or higher using command-line arguments, for example: python mcp_server.py --port 8000 --host 0.0.0.0. Then use an MCP client (e.g., VSCode Cline) to send notification commands over the MCP protocol.
Requires Python 3.8 or higher. On Windows, the win10toast library is needed; on macOS, osascript is built-in.
It uses the MCP protocol over TCP with configurable network interfaces (e.g., 0.0.0.0). No authentication is documented.
No, each server instance runs on one operating system and uses that OS’s notification method.
Title, message content, display duration, optional icon (Windows only), optional subtitle (macOS only), optional sound (macOS only), and notification type (info, warning, error, success).
Default host is localhost (127.0.0.1) and default port is 8000. Both are configurable via command-line arguments or environment variables.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Model Context Protocol Servers
Open-source MCP to use Blender with any LLM

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Comments