ntfy-mcp MCP Server

What does “ntfy-mcp” MCP Server do?

ntfy-mcp is an MCP (Model Context Protocol) server that acts as a notification bridge between AI assistants and the ntfy notification service. Its main function is to notify users whenever their AI assistant completes a task, allowing for seamless and non-intrusive updates. By integrating with MCP, ntfy-mcp enables development workflows that benefit from instant, cross-device notifications—such as alerting users when code execution, data processing, or other automated tasks complete. This ensures users stay informed in real time without constantly monitoring their environment, thereby boosting productivity and reducing context switching.

List of Prompts

• No specific prompt templates are listed in the repository.

List of Resources

• No explicit MCP resources are documented or exposed in the available content.

List of Tools

• notify_user
  Sends a notification to a specified ntfy topic when an AI assistant completes a task. This is the primary tool exposed by ntfy-mcp for integrating notifications into development workflows.

Use Cases of this MCP Server

• Task Completion Alerts
  Developers can receive notifications on their phone or device when long-running or background tasks initiated by their AI assistant are finished.
• Remote Monitoring
  Stay updated on the status of automated workflows or scripts without having to manually check their progress.
• Enhanced Productivity
  Frees up users from constant monitoring, allowing them to focus on other tasks while being assured they’ll be notified when important events occur.
• Integration with DevOps
  Receive deployment, build, or CI/CD pipeline completion notifications through ntfy, ensuring timely responses and reducing downtime.
• User Experience Improvements
  Adds a layer of user-friendliness to AI-driven tooling by making sure users are kept in the loop effortlessly.

How to set it up

Windsurf

1. Ensure Node.js is installed.
2. Clone the repository and run npm install and npm run build.
3. Locate the Windsurf MCP configuration file.
4. Add the ntfy-mcp server using the following JSON snippet.
5. Save changes and restart Windsurf.

"mcpServers": {
  "ntfy-mcp": {
    "command": "node",
    "args": [
      "/path/to/ntfy-mcp/build/index.js"
    ],
    "env": {
      "NTFY_TOPIC": "<your topic name>"
    },
    "autoApprove": [
      "notify_user"
    ]
  }
}

Claude

1. Install Node.js and clone/build ntfy-mcp as above.
2. Open Claude’s config file for MCP servers.
3. Insert the ntfy-mcp configuration as shown below.
4. Restart Claude for changes to take effect.

"mcpServers": {
  "ntfy-mcp": {
    "command": "node",
    "args": [
      "/path/to/ntfy-mcp/build/index.js"
    ],
    "env": {
      "NTFY_TOPIC": "<your topic name>"
    },
    "autoApprove": [
      "notify_user"
    ]
  }
}

Cursor

1. Make sure Node.js is available and ntfy-mcp is built.
2. Edit Cursor’s MCP server configuration file.
3. Add ntfy-mcp server details using the JSON template below.
4. Save and restart Cursor.

"mcpServers": {
  "ntfy-mcp": {
    "command": "node",
    "args": [
      "/path/to/ntfy-mcp/build/index.js"
    ],
    "env": {
      "NTFY_TOPIC": "<your topic name>"
    },
    "autoApprove": [
      "notify_user"
    ]
  }
}

Cline

1. Install Node.js, then clone/build ntfy-mcp.
2. Access the Cline MCP server configuration.
3. Insert the server details as in the following example.
4. Save and restart Cline.
5. Download the ntfy app and subscribe to your topic.

"ntfy-mcp": {
  "command": "node",
  "args": [
    "/path/to/ntfy-mcp/build/index.js"
  ],
  "env": {
    "NTFY_TOPIC": "<your topic name>"
  },
  "autoApprove": [
    "notify_user"
  ]
}

Securing API Keys

Store topic names or sensitive keys in environment variables rather than hard-coding them. Example:

"env": {
  "NTFY_TOPIC": "${NTFY_TOPIC}"
},
"inputs": {
  "topic": "${NTFY_TOPIC}"
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "ntfy-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “ntfy-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

This MCP server is highly focused and simple, providing a single useful tool (notify_user) for notification purposes. Its documentation is clear and the setup is straightforward, but it lacks prompt templates, resource definitions, and advanced MCP features like sampling or roots. It is best rated for its simplicity and targeted use-case.

MCP Score