ntfy-mcp-server

What is ntfy-mcp-server?

ntfy-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants to send push notifications through the ntfy.sh pub-sub service. It is designed for developers and users who want to integrate real-time notifications into their AI workflows.

How to use ntfy-mcp-server?

Install dependencies (npm install --save-dev typescript @types/node ts-node), build the TypeScript code (npm run build), then run the server (npm start) or point your MCP client to ./build/index.js. The server exposes a single tool send_message with parameters for channel, message, title, priority, and tags.

Key features of ntfy-mcp-server

• 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

Use cases of ntfy-mcp-server

• Get notified when long-running tasks complete
• Receive alerts from automated workflows
• Stay informed about important events in applications

FAQ from ntfy-mcp-server

What dependencies are required to run ntfy-mcp-server?

Node.js, TypeScript, and ts-node are required; install them via npm.

Does ntfy-mcp-server require authentication?

No, the server uses the public ntfy.sh service and no authentication is required for public channels.

How are channel names chosen?

Channel names can be any string but should be unique; anyone who knows the name can send messages to it.

What is the default server endpoint?

The server uses the public ntfy.sh service at https://ntfy.sh/.

What parameters does the send_message tool accept?

It accepts channel (required), message (required), title (optional), priority (1-5, optional), and tags (optional array).