📌Overview

Purpose: To provide a server that sends desktop notifications with sound effects when agent tasks are completed.

Overview: MCP Notify Server is a cross-platform application designed to enhance user interaction and alertness by delivering notifications directly to the desktop upon task completion. It utilizes the standard MCP protocol, allowing integration with various language model clients.

Key Features:

• Desktop Notifications: Sends system alerts after agent task completion, ensuring immediate user awareness.

• Sound Alerts: Plays predefined alert sounds to further grab user attention, enhancing the notification experience.

• Cross-Platform Compatibility: Supports major operating systems including Windows, macOS, and Linux, making it accessible to a wide range of users.

• Standard MCP Protocol Integration: Facilitates seamless interoperability with various LLM clients, broadening its utility.

---

MCP Notify Server

A MCP server that sends desktop notifications with sound effects when agent tasks are completed.

Features

• Send system desktop notifications after agent task completion
• Play alert sounds to grab user attention, with included sound files
• Cross-platform support (Windows, macOS, Linux)
• Based on standard MCP protocol, integrates with various LLM clients

Installation

Install using uv package manager

git clone https://github.com/Cactusinhand/mcp_server_notify.git
cd mcp_server_notify

uv venv
source .venv/Scripts/activate

uv pip install mcp-server-notify
# or
pip install mcp-server-notify

After installation, call the module directly to check if installation was successful:

python -m mcp_server_notify

This module accepts --debug or --file options, for example:

python -m mcp_server_notify --debug
python -m mcp_server_notify --debug --log-file=path/to/logfile.log

Special Requirements

We use the Apprise API for desktop notification delivery, so some additional requirements must be installed for your operating system:

Windows

pip install pywin32

macOS

Make sure terminal-notifier is installed:

brew install terminal-notifier

Usage

Using with Claude Desktop

Find the configuration file claude_desktop_config.json and set it as follows:

{
    "mcpServers": {
        "NotificationServer": {
            "command": "uv",
            "args": [
              "--directory",
              "path/to/your/mcp_server_notify project",
              "run",
              "mcp-server-notify"
            ]
        }
    }
}

If installed globally, you can also use the python command:

{
    "mcpServers": {
        "NotificationServer": {
            "command": "python",
            "args": [
              "-m",
              "mcp_server_notify"
            ]
        }
    }
}

Using with Cursor

Find the configuration file ~/.cursor/mcp.json or your_project/.cursor/mcp.json and configure:

{
    "mcpServers": {
        "NotificationServer": {
            "command": "uv",
            "args": [
              "--directory",
              "path/to/your/mcp_server_notify project",
              "run",
              "mcp-server-notify"
            ]
        }
    }
}

After configuration, add a prompt like:

finally, send me a notification when task finished.

at the end of your task input to the AI to trigger notifications.

You can also add this prompt as a rule in Cursor Settings → Rules to automate it.

Running with Docker

Currently not supported due to environment compatibility issues.

Challenges include:

• OS-specific notification systems
• Docker container isolation limiting access to host resources
• Managing dependencies across different operating systems

License

MIT

Contributions

Issues and pull requests are welcome!