Overview
What is MCP Notify Server?
MCP Notify Server is an MCP (Model Context Protocol) server that sends desktop notifications with sound effects when AI agent tasks are completed. It integrates with various LLM clients and supports Windows, macOS, and Linux.
How to use MCP Notify Server?
Install via pip install mcp-server-notify or uv pip install mcp-server-notify. After installation, add the server configuration to your MCP client (e.g., Claude Desktop, Cursor, or VSCode). Add a prompt such as "finally, send me a notification when task finished." to trigger the notification. For Windows, additionally install pywin32; for macOS, install terminal-notifier via Homebrew.
Key features of MCP Notify Server
- Sends system desktop notifications after agent task completion
- Plays alert sounds to grab user attention
- Cross‑platform support (Windows, macOS, Linux)
- Built on the standard MCP protocol for easy LLM integration
Use cases of MCP Notify Server
- Notify users when a long-running AI agent task finishes
- Provide an audible alert for completed background analyses
- Get desktop pop‑ups from LLM‑based coding assistants (e.g., Cursor, Claude)
FAQ from MCP Notify Server
How does MCP Notify Server send notifications?
It uses the Apprise API for delivering desktop notifications and includes a bundled sound file for audio alerts.
What dependencies are required per platform?
Windows requires pywin32. macOS requires terminal-notifier (installable via brew). Linux has no additional dependencies listed.
Can MCP Notify Server run in Docker?
No, Docker is not currently supported due to environment compatibility issues with host notification systems.
What prompt do I need to add to trigger a notification?
Add a phrase such as “finally, send me a notification when task finished.” at the end of your task input to the AI agent.
How can I test the installation?
Run python -m mcp_server_notify with optional --debug or --file flags to verify the module works correctly.
