MCP Notify Server logo

MCP Notify Server

by Cactusinhand

MCP Notify Server sends desktop notifications with sound effects when agent tasks are completed. It integrates with various LLM clients using the standard MCP protocol.

View on GitHub

Last updated: N/A

What is MCP Notify Server?

MCP Notify Server is a server that provides desktop notifications with sound alerts upon the completion of agent tasks. It's designed to integrate with LLM clients using the MCP protocol, alerting users when their AI tasks are finished.

How to use MCP Notify Server?

To use the server, install it using uv or pip. Configure your LLM client (e.g., Claude Desktop, Cursor) to use the MCP server by specifying the command and arguments in the client's configuration file. Then, instruct the AI to send a notification upon task completion by including a prompt like 'finally, send me a notification when task finished.'

Key features of MCP Notify Server

  • Sends system desktop notifications after agent tasks completion

  • Plays alert sounds to grab user attention

  • Cross-platform support (Windows, macOS, Linux)

  • Based on standard MCP protocol, integrates with various LLM clients

Use cases of MCP Notify Server

  • Notifying users upon completion of long-running AI tasks

  • Alerting developers when code generation or analysis is finished

  • Integrating with LLM-powered workflows to provide real-time feedback

  • Using with Claude Desktop for notification of task completion

  • Using with Cursor for notification of task completion

FAQ from MCP Notify Server

How do I install the server?

You can install it using uv or pip. Follow the instructions in the Installation section of the README.

How do I configure my LLM client to use the server?

Modify the LLM client's configuration file (e.g., claude_desktop_config.json, ~/.cursor/mcp.json) to include the MCP server details.

What operating systems are supported?

Windows, macOS, and Linux are supported.

Why is Docker not supported?

Docker support is currently unavailable due to environment compatibility issues related to OS-specific notification systems and Docker isolation.

How do I trigger a notification?

Add a prompt like 'finally, send me a notification when task finished.' at the end of your task input to the AI.