Notify MCP Server

@longdog

Basic information

About Notify MCP Server

A lightweight Bash-based Model Context Protocol (MCP) server for sending desktop notifications via notify-send. This zero-dependency server enables AI assistants like Claude, Cursor, and VS Code to send system notifications directly to your Linux desktop.

#linux#gnome#notify

Notify MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "notify": {
      "command": "/home/username/notify-mcp/notify-mcp.sh",
      "args": []
    }
  }
}

Notify MCP Server tools

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.

Overview

What is Notify Mcp?

Notify Mcp is a lightweight Bash-based Model Context Protocol (MCP) server that sends desktop notifications via notify-send. It enables AI assistants like Claude, Cursor, and VS Code to deliver system notifications to Linux desktops and macOS.

How to use Notify Mcp?

Clone the repository, make the script executable, and optionally add it to your PATH. Configure the server in your AI assistant’s MCP settings (Claude Desktop, Cursor, VS Code, or Gemini CLI) by specifying the absolute path to notify-mcp.sh as a command‑type stdio server. For testing, you can pipe JSON‑RPC requests directly to the script.

Key features of Notify Mcp

Zero‑dependency Bash MCP server (requires only notify-send and jq)
Sends Linux desktop and macOS notifications from AI assistants
Works with Claude Desktop, Cursor, VS Code, and Gemini CLI
Simple stdio‑based transport for direct interaction
Lightweight, single‑script implementation

Use cases of Notify Mcp

AI assistant notifies you when a long‑running task completes
Receive desktop alerts for code reviews or build failures from an IDE
Get a system toast when a CLI‑based AI session finishes a command
Trigger custom notifications from any MCP‑compatible agent

Frequently asked questions

What does Notify Mcp do?

It is an MCP server that calls the system’s `notify-send` command to display desktop notifications, allowing AI tools to pop up messages on Linux and macOS.

What prerequisites does Notify Mcp require?

A Linux system with `libnotify` (providing `notify-send`) or macOS, plus the `jq` command for JSON processing.

How do I install notify-send on Linux?

On Ubuntu/Debian: `sudo apt-get install libnotify-bin`. Fedora/RHEL: `sudo dnf install libnotify`. Arch: `sudo pacman -S libnotify`. Alt Linux: `sudo apt-get install notify-send`.

Which AI assistants can I use with Notify Mcp?

Claude Desktop, Cursor IDE, VS Code (via the GitHub Copilot extension), and Gemini CLI are explicitly documented.

Does Notify Mcp require internet or an API key?

No. The server runs locally using stdio transport; no network connection or authentication is needed.

Comments

More Developer Tools MCP servers

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

Eddyter AI Rich Text Editor MCP

EddyterAI

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Screen Browser

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.