Ntfy MCP Server

An MCP (Model Context Protocol) server designed to interact with the ntfy push notification service. It enables LLMs and AI agents to send notifications to your devices with extensive customization options.

Table of Contents

• Overview

• Features

• Quick Start

• Installation

• Configuration

• Project Structure

• Tools

• Resources

• Use Cases

• Available Scripts

• Contributing

• License

Overview

This server implements the Model Context Protocol (MCP), enabling standardized communication between LLMs and external systems. Specifically, it provides an interface to the ntfy push notification service.

Ntfy is a simple HTTP-based pub-sub notification service that allows you to send notifications to your phone or desktop via simple HTTP requests. With this MCP server, LLM agents like Claude can send notifications to you through ntfy without needing direct HTTP access.

Features

• MCP Server Implementation: Built using the @modelcontextprotocol/sdk for seamless integration with LLM agents.

• Ntfy Integration: Provides a tool (send_ntfy) to send notifications with support for:

  • Message prioritization (1-5 levels)

  • Emoji tags

  • Clickable actions and buttons

  • File attachments

  • Delayed delivery

  • Markdown formatting

• Resource Exposure: Exposes the configured default ntfy topic as an MCP resource.

• TypeScript: Modern, type-safe codebase with comprehensive type definitions.

• Structured Logging: Uses winston and winston-daily-rotate-file for detailed and rotatable logs.

• Configuration Management: Uses dotenv for easy environment-based configuration.

• Utility Scripts: Includes scripts for cleaning build artifacts and generating directory structure documentation.

• Error Handling & Security: Implements robust error handling, input sanitization (sanitize-html), and security filters (xss-filters).

Quick Start

1. Prerequisites:

   • Node.js (v16+)

   • npm or yarn

   • An MCP-compatible client (Claude Desktop, Cline, etc.)

2. Install and Run:

   # Option 1: Install via npm npm install -g ntfy-mcp-server # Option 2: Clone repository and build git clone https://github.com/cyanheads/ntfy-mcp-server.git cd ntfy-mcp-server npm install npm run build # Create .env file (optional but recommended) cp .env.example .env # Edit .env to set NTFY_DEFAULT_TOPIC # Start the server npm start

3. Add to MCP Client Settings: Add the server to your MCP client settings file (see Configuration)

4. Use the tool: Once connected, you can use the send_ntfy tool to send notifications.

Installation

Option 1: NPM Package (Recommended)

1. Install the package globally:

   npm install -g ntfy-mcp-server

   This will install the server globally, making it available as a command-line tool.

2. Or install locally in your project:

   npm install ntfy-mcp-server

   When installed locally, you can run it via npx or from node.

Option 2: From Source

1. Clone the repository:

   git clone https://github.com/cyanheads/ntfy-mcp-server.git cd ntfy-mcp-server

2. Install dependencies:

   npm install

3. Build the project:

   npm run build

Configuration

Environment Variables

Create a .env file in the project root based on .env.example:

MCP Client Settings

For Cline VSCode Extension

Add the following configuration to your Cline MCP settings file (usually located at ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json on macOS):

If installed globally:

If installed from source:

For Claude Desktop App

Add the following configuration to your Claude Desktop config file (usually located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

If installed globally:

If installed from source:

For source installation, replace Adjust

Ntfy Setup

1. Install the ntfy app on your devices from ntfy.sh or the app stores

2. Subscribe to your topic in the app

3. Use the same topic in your MCP server configuration

Project Structure

Tools

send_ntfy

Sends a notification message via the ntfy service.

Key Arguments:

Example Usage:

Example Response:

Resources

Direct Resources

ntfy://default

• Description: Returns the default ntfy topic configured in the server's environment variables (NTFY_DEFAULT_TOPIC).

• Usage: Useful for clients to discover the primary topic without needing prior configuration.

• Example: An LLM agent can access this resource to automatically use the default topic when sending notifications.

• Example Response:

  { "defaultTopic": "ATLAS", "timestamp": "2025-03-27T08:30:25.619Z", "requestUri": "ntfy://default", "requestId": "0da963d0-30e0-4dbc-bb77-4bf2dee14484" }

Resource Templates

ntfy://{topic}

• Description: Returns information about a specific ntfy topic.

• Parameters: topic - The name of the ntfy topic.

• Usage: For querying information about topics other than the default.

• Example Response:

  { "topic": "ATLAS", "timestamp": "2025-03-27T08:30:30.038Z", "requestUri": "ntfy://ATLAS", "requestId": "31baf1df-278f-4fdb-860d-019f156a72b0" }

Use Cases

1. Long-running Task Notifications - Get notified when tasks like database backups, code generation, or data processing complete.

2. Scheduled Reminders - Set delayed notifications for future events or reminders.

3. Alert Systems - Set up critical alerts for monitoring systems or important events.

4. Mobile Notifications from LLMs - Allow LLMs to send notifications directly to your phone.

5. Multi-step Process Updates - Receive updates as different stages of a complex process complete.

Usage Examples

Basic Notification

Rich Notification with Actions

Available Scripts

• npm run build: Compiles the TypeScript source code to JavaScript in the dist/ directory.

• npm run clean: Removes the dist/ directory and cleans the contents of the logs/ directory.

• npm run rebuild: Runs clean and then build.

• npm run tree: Generates a directory tree representation in docs/tree.md.

• npm start: Runs the compiled server from the dist/ directory using Node.js.

• npm run watch: Tails the combined log file (logs/combined.log) for real-time monitoring.

Contributing

Contributions are welcome! Please feel free to submit pull requests or open issues to improve the project.

1. Fork the repository.

2. Create a feature branch (git checkout -b feature/your-feature).

3. Commit your changes (git commit -m 'Add some feature').

4. Push to the branch (git push origin feature/your-feature).

5. Create a new Pull Request.

For bugs and feature requests, please create an issue on the repository.

Development Best Practices

• Follow TypeScript best practices and maintain strong typing

• Write tests for new functionality

• Keep dependencies up to date

• Follow the existing code style and patterns

License

This project is licensed under the Apache-2.0 License. See the LICENSE file for details.

Acknowledgements

• ntfy.sh for providing the notification service

• Model Context Protocol for enabling LLM-to-tool connections

• All contributors and users of this project