ntfy-me-mcp

A streamlined Model Context Protocol (MCP) server for sending notifications via ntfy service (public or selfhosted with token support) 📲

ntfy-me-mcp provides AI assistants with the ability to send real-time notifications to your devices through the ntfy service (either public or selfhosted with token support). Get notified when your AI completes tasks, encounters errors, or reaches important milestones - all without constant monitoring.

The server includes intelligent features like automatic URL detection for creating view actions and smart markdown formatting detection, making it easier for AI assistants to create rich, interactive notifications without extra configuration.

Name	Link / Badge
Glama.ai
Smithery.ai
MseeP.ai
Archestra.ai

• Features
  • Coming soon...
• Quickstart - MCP Server Configuration
  • Configuration Examples
  • VS Code Token Input Example
• Installation
  • Option 1: Install Globally
  • Option 2: Run with npx
  • Option 3: Install Locally
  • Option 4: Build and Use Locally
    • Using locally built server with MCP
  • Option 5: MCP Marketplace Installations
• Configuration
  • Environment Variables
• Usage
  • Authentication
  • Setting Up the Notification Receiver
  • Sending Notifications (ntfy_me tool)
    • Using Natural Language
    • Message Parameters
    • Action Links
    • Emoji Shortcodes
    • Markdown Formatting
  • Retrieving Messages (ntfy_me_fetch tool)
    • Using Natural Language
    • Message Parameters
    • Examples
  • Development
    • Building from Source
• License
• Contributing

• 🚀 Quick Setup: Run with npx or docker!
• 🔔 Real-time Notifications: Get updates on your phone/desktop when tasks complete
• 🎨 Rich Notifications: Support for topic, title, priorities, emoji tags, and detailed messages
• 🔍 Notification Fetching: Fetch and filter cached messages from your ntfy topics
• 🎯 Smart Action Links: Automatically detects URLs in messages and creates view actions
• 📄 Intelligent Markdown: Auto-detects and enables markdown formatting when present
• 🔒 Secure: Optional authentication with access tokens
• 🔑 Input Masking: Securely store your ntfy token in your vs config!
• 🌐 Self-hosted Support: Works with both ntfy.sh and self-hosted ntfy instances

• 📨 Email: Send notifications to email (requires ntfy email server configuration)
• 🔗 Click urls: Ability to customize click urls
• 🖼️ Image urls: Intelligent image url detection to automatically include image urls in messages and notifications
• 🏁 and more!

Choose the config shape that matches your client. All examples below use NTFY_TOPIC as the required variable and keep the optional auth settings commented out until you need them.

{
  "ntfy-me-mcp": {
    "command": "npx",
    "args": ["-y", "ntfy-me-mcp"],
    "env": {
      "NTFY_TOPIC": "your-ntfy-topic",
      "NTFY_URL": "https://ntfy.sh",
      // "NTFY_TOKEN": "add-your-ntfy-token"
    }
  }
}

{
  "ntfy-me-mcp": {
    "command": "node",
    "args": ["/absolute/path/to/ntfy-me-mcp/build/index.js"],
    "env": {
      "NTFY_TOPIC": "your-ntfy-topic",
      "NTFY_URL": "https://ntfy.sh",
      // "NTFY_TOKEN": "add-your-ntfy-token"
    }
  }
}

{
  "ntfy-me-mcp": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "-e",
      "NTFY_TOPIC",
      "-e",
      "NTFY_URL",
      "-e",
      "NTFY_TOKEN",
      "gitmotion/ntfy-me-mcp:latest"
    ],
    "env": {
      "NTFY_TOPIC": "your-ntfy-topic",
      "NTFY_URL": "https://ntfy.sh",
      // "NTFY_TOKEN": "add-your-ntfy-token"
    }
  }
}

{
  "ntfy-me-mcp": {
    "enabled": true,
    "type": "local",
    "command": ["npx", "-y", "ntfy-me-mcp"],
    "environment": {
      "NTFY_TOPIC": "your-ntfy-topic",
      "NTFY_URL": "https://ntfy.sh",
      // "NTFY_TOKEN": "add-your-ntfy-token"
    }
  }
}

Docker images:

• gitmotion/ntfy-me-mcp:latest (Docker Hub)
• ghcr.io/gitmotion/ntfy-me-mcp:latest (GitHub Container Registry)

Replace /absolute/path/to/ntfy-me-mcp/build/index.js with the real path on your machine after running npm run build.

If your client supports prompt-based secret inputs (i.e. VS Code), prefer that over hardcoding NTFY_TOKEN in config files. (Otherwise use your token directly)

Use matching values like this in your mcp.json file:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "ntfy_token",
      "description": "Ntfy Token",
      "password": true
    }
  ],
  "servers": {
    "ntfy-me-mcp": {
      "command": "npx",
      "args": ["-y", "ntfy-me-mcp"],
      "env": {
        "NTFY_TOPIC": "your-ntfy-topic",
        "NTFY_URL": "https://your-ntfy-server.com",
        "NTFY_TOKEN": "${input:ntfy_token}"
      }
    }
  }
}

• Add this to your VS Code mcp.json file, either the user-level file or your workspace .vscode/mcp.json
• Set NTFY_TOKEN exactly to "${input:ntfy_token}" when you want VS Code to treat it as a secure prompt-backed value.

If the client resolves "${input:ntfy_token}" before launch, the server receives the real token directly. If the placeholder is passed through unchanged, ntfy-me-mcp detects that unresolved input reference and prompts for the token itself at startup.

If you need to install and run the server directly (alternative to the MCP configuration above):

npm install -g ntfy-me-mcp

npx ntfy-me-mcp

# Clone the repository
git clone https://github.com/gitmotion/ntfy-me-mcp.git
cd ntfy-me-mcp

# Install dependencies
npm install

# Copy the example environment file and configure it
cp .env.example .env
# Edit .env with your preferred editor and update the variables
# nano .env  # or use your preferred editor

# Build the project
npm run build

# Start the server
npm start

If you're developing or customizing the server, you might want to run it directly with node:

# Clone the repository
git clone https://github.com/gitmotion/ntfy-me-mcp.git
cd ntfy-me-mcp

# Install dependencies
npm install

# Copy the example environment file and configure it
cp .env.example .env
# Edit the .env file to set your NTFY_TOPIC and other optional settings
# nano .env  # or use your preferred editor

# Build the project
npm run build

# Run using node directly
npm start

When configuring your MCP to use a locally built version, specify the node command and path to the built index.js file:

{
  "ntfy-me": {
    "command": "node",
    "args": ["/path/to/ntfy-mcp/build/index.js"],
    "env": {
      "NTFY_TOPIC": "your-topic-name",
      //"NTFY_URL": "https://your-ntfy-server.com", // Use if using a self-hosted server
      //"NTFY_TOKEN": "your-auth-token" // Use if using a protected topic/server
    }
  }
}

For secure token handling in VS Code, replace the commented NTFY_TOKEN line with "NTFY_TOKEN": "${input:ntfy_token}" and define the ntfy_token prompt in the same mcp.json file under the top-level inputs array.

Remember to use the absolute path to your build/index.js file in the args array.

To install ntfy-me-mcp for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gitmotion/ntfy-me-mcp --client claude

Create a .env file in your project directory by copying the provided example:

# Copy the example file
cp .env.example .env

# Edit the file with your preferred editor
nano .env  # or vim, code, etc.

Your .env file should contain these variables:

# Required
NTFY_TOPIC=your-topic-name

# Optional - Configure these if using a private/protected ntfy server
# NTFY_URL=https://ntfy.sh  # Default is ntfy.sh, change to your self-hosted ntfy server URL if needed
                            # Include port if needed, e.g., https://your-ntfy-server.com:8443
# NTFY_TOKEN=your-access-token  # Required for authentication with protected topics/servers

This server supports both authenticated and unauthenticated ntfy endpoints:

• Public Topics: When using public topics on ntfy.sh or other public servers, no authentication is required.
• Protected Topics: For protected topics or private servers, you need to provide an access token.

If authentication is required but not provided, you'll receive a clear error message explaining how to add your token.

1. Install the ntfy app on your device
2. Subscribe to your chosen topic (the same as your NTFY_TOPIC setting)

This section covers all functionality related to sending notifications using the ntfy_me tool.

When working with your AI assistant, you can use natural phrases like:

"Send me a notification when the build is complete"
"Notify me when the task is done"
"Alert me after generating the code"
"Message me when the process finishes"
"Send an alert with high priority"

The tool accepts these parameters:

Example:

{
  taskTitle: "Code Generation Complete",
  taskSummary: "Your React component has been created successfully with proper TypeScript typing.",
  priority: "high",
  tags: ["check", "code", "react"]
}

This will send a high-priority notification with a checkmark emoji.

You can add clickable action buttons to your notifications using the actions parameter, or let the server automatically detect URLs in your message.

When URLs are present in the message body, the server automatically creates up to 3 view actions (ntfy's maximum limit) from the first detected URLs. This makes it easy to include clickable links without manually specifying the actions array.

For example, this message:

{
  taskTitle: "Build Complete",
  taskSummary: "Your PR has been merged! View the changes at https://github.com/org/repo/pull/123 or check the deployment at https://staging.app.com"
}

Will automatically generate view actions for both URLs, making them easily clickable in the notification.

For more control, you can manually specify actions:

Example with action links:

{
  taskTitle: "Pull Request Review",
  taskSummary: "Your code has been reviewed and is ready for final checks",
  priority: "high",
  tags: ["check", "code"],
  actions: [
    {
      action: "view",
      label: "View PR",
      url: "https://github.com/org/repo/pull/123"
    },
    {
      action: "view",
      label: "View Changes",
      url: "https://github.com/org/repo/pull/123/files",
      clear: true
    }
  ]
}

You can use emoji shortcodes in your tags for visual indicators:

• warning → ⚠️
• check → ✅
• rocket → 🚀
• tada → 🎉

See the full list of supported emoji shortcodes.

Your notifications support rich markdown formatting with intelligent detection! When you include markdown syntax in your taskSummary, the server automatically detects it and enables markdown parsing - no need to set markdown: true explicitly.

The server checks for common markdown patterns like:

• Headers (#, ##, etc.)
• Lists (-, *, numbers)
• Code blocks (```)
• Links (text)
• Bold/italic (text, text)

When these patterns are detected, markdown parsing is automatically enabled for the message.

While automatic detection works in most cases, you can still explicitly control markdown parsing:

{
  taskTitle: "Task Complete",
  taskSummary: "Regular plain text message",
  markdown: false  // Force disable markdown parsing
}

This section covers all functionality related to fetching and filtering messages using the ntfy_me_fetch tool.

AI assistants understand various ways to request message fetching:

"Show me my recent notifications"
"Get messages from the last hour"
"Find notifications with title 'Build Complete'"
"Search for messages with the test_tube tag"
"Show notifications from the updates topic from the last 24hr"
"Check my latest alerts"

The tool accepts these parameters:

1. Fetch Recent Messages

{
  since: "30m"; // Get messages from last 30 minutes
}

2. Filter by Title and Priority

{
  messageTitle: "Build Complete",
  priorities: "high",
  since: "1d"
}

3. Search Different Topic with Tags

{
  ntfyTopic: "updates",
  tags: ["error", "warning"],
  since: "all"
}

4. Find Specific Message

{
  messageId: "xxxxXXXXxxxx";
}

Messages are returned with full details including:

• Message ID and timestamp
• Topic and title
• Content and priority
• Tags and attachments
• Action links and expiration

Note: Message history availability depends on your ntfy server's cache settings. The public ntfy.sh server typically caches messages for 12 hours.

Development and contribution guidance now lives in CONTRIBUTING.md, including setup steps and the npm scripts reference.

This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.

Made with ❤️ by gitmotion