mcpField
N
ntfy-mcp-server

ntfy-mcp-server

Local
github.com/mounta11nCommunication0Updated 72w ago

About ntfy-mcp-server

ntfy-mcp-server is an MCP server for AI assistants that sends push notifications through ntfy.sh. It supports channel messages with optional titles, priorities, and tags.

Key features

  1. 01Send messages to ntfy.sh channels
  2. 02Set notification titles
  3. 03Choose priorities from 1–5
  4. 04Add tags to messages

Use cases

  1. 01Get notified when long tasks finish
  2. 02Receive alerts from automated workflows
  3. 03Send application event notifications to devices

MCP support

It exposes the `send_message` tool to MCP clients, which sends a message to a specified ntfy.sh channel with optional title, priority, and tags.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ntfy MCP Server

A Model Context Protocol (MCP) server that enables AI assistants to send push notifications through ntfy.sh. This server provides a simple way to integrate real-time notifications into your AI workflows, allowing you to receive alerts on your phone, desktop, or any device that supports ntfy.sh.

What is ntfy.sh?

ntfy.sh is a simple HTTP-based pub-sub notification service that allows you to send push notifications to your devices. It's particularly useful for:

  • Getting notified when long-running tasks complete
  • Receiving alerts from automated workflows
  • Staying informed about important events in your applications

Features

  • Send messages to any ntfy.sh channel
  • Support for message titles, priorities (1-5), and tags
  • Simple integration with MCP-compatible AI assistants
  • No authentication required for public channels

Installation

  1. Install dependencies:
npm install --save-dev typescript @types/node ts-node
  1. Build the TypeScript code:
npm run build
  1. The MCP server is now available at ./build/index.js

Usage

Running the Server

After building, you can run the server directly:

npm start

Or point your MCP client to the built server at ./build/index.js.

Available Tools

The server provides one tool:

send_message

Sends a message to a specified ntfy.sh channel.

Parameters:

  • channel (required): The ntfy.sh channel name to send the message to
  • message (required): The message content to send
  • title (optional): A title for the notification
  • priority (optional): Priority level from 1-5 (5 being highest priority)
  • tags (optional): Array of tags to categorize the message

Example usage in an MCP client:

{
  "tool": "send_message",
  "arguments": {
    "channel": "my-notifications",
    "message": "Task completed successfully!",
    "title": "Workflow Update",
    "priority": 4,
    "tags": ["automation", "success"]
  }
}

Configuration

No additional configuration is required. The server uses the public ntfy.sh service at https://ntfy.sh/.

Channel Names
  • Channel names can be any string, but should be unique to avoid conflicts
  • Consider using descriptive names like my-project-alerts or personal-notifications
  • Anyone who knows your channel name can send messages to it, so choose wisely

Development

Build Scripts
  • npm run build - Compile TypeScript to JavaScript
  • npm run build:linux - Build and make executable on Linux
  • npm run build:windows - Build for Windows
  • npm start - Run the compiled server
Project Structure

License

See LICENSE file for details.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.