M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
N

ntfy-me MCP Server

Community
MCP server for sending/fetching ntfy notifications from AI agents
How to install ↓ Compare GitHub source repository ↗
Category
Other #71 of 230
Stars
★ 76 Popular
Transport
stdio (local process)
Runtime
Node.js · Docker
Credentials
Optional API key
License
GPL-3.0
Last commit
Tools
2
60FMRS · C

ntfy-me-mcp is a practical tool that lets AI agents easily send and fetch ntfy notifications. It supports public and self-hosted servers, offering rich notification features like priority, tags, and markdown. Installation is straightforward via npx or Docker. Security is addressed with token auth, though privacy on public topics is a consideration.

Strongest · Documentation 14/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
14/20
Maintenance
12/20
Documentation
14/20
Setup experience
12/20
Why each score
Reliability 8/20
The server is TypeScript-based, using MCP SDK 1.29.0, with no apparent contradictions. However, static review cannot verify startup process or tool declarations against actual behavior, and no tests or CI evidence are present, so reliability score is limited (≤12).
Security and permissions 14/20
Optional token authentication is supported, and documentation emphasizes secure token handling (e.g., VS Code input prompts). No malicious code or overreach detected, but tokens may be passed via environment variables or tool parameters, posing potential leakage risk. No confirmation mechanism for sensitive operations, but overall security risk is controllable.
Maintenance 12/20
Repository is active, with 70 stars, 3 open issues, and not archived. License is GPL-3.0. However, no clear evidence of dependency update policy or security response channel, indicating governance gaps.
Documentation 14/20
README provides detailed configuration examples, tool parameter explanations, environment variable table, authentication notes, and examples. But troubleshooting section is missing, and limits (like rate limits) or costs are not disclosed. Documentation is usable but with hidden assumptions.
Setup experience 12/20
Multiple installation methods are provided (npx, Docker, local build), with config examples for various clients. However, no CI/CD or test evidence, and static review cannot verify reliability of installation steps, so score is limited.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Developers wanting to integrate AI workflows with mobile/desktop notifications
  • AI agents that need task completion or error alerts
  • Users of ntfy.sh or self-hosted ntfy instances

Not for

  • Those who need email or image notifications (coming soon)
  • Users needing complex notification workflows
  • Those who require non-ntfy services

Required permissions

  • Send notifications to configured ntfy topics
  • Fetch messages from configured ntfy topics
  • Network access to reach the ntfy server

Risks and side effects

  • Notifications may be publicly readable if the topic is public and no token is used
  • Potential unauthorized access if the token is leaked
  • Dependence on ntfy service availability

Setup

Before you start

Runtime：Node.js · Docker

NTFY_TOPIC required The ntfy topic to publish notifications to; subscribe to it in your ntfy app. Required.
NTFY_TOKEN optionalsecret Access token for protected topics or private servers; optional, obtain it from your ntfy server's access token settings.
Other optional settings (1)
NTFY_URL optional ntfy server URL, defaults to https://ntfy.sh; change it for self-hosted instances (include port if needed).
  1. Install the ntfy app on your device (https://ntfy.sh/app) or deploy your own ntfy server.
  2. Add the server to your MCP client configuration using npx, Docker, or local install.
  3. Set environment variables: NTFY_TOPIC (required), NTFY_URL (optional, defaults to https://ntfy.sh), and NTFY_TOKEN (optional).
  4. Run with npx ntfy-me-mcp or install globally with npm install -g ntfy-me-mcp.
claude_desktop_config.json 
{
  "mcpServers": {
    "ntfy-me-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ntfy-me-mcp"
      ],
      "env": {
        "NTFY_TOPIC": "your-ntfy-topic",
        "NTFY_URL": "https://ntfy.sh",
        "NTFY_TOKEN": "your-access-token"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

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

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add ntfy-me-mcp -e NTFY_TOPIC=your-ntfy-topic -e NTFY_URL=https://ntfy.sh -e NTFY_TOKEN=your-access-token -- npx -y ntfy-me-mcp

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After configuring the client, confirm the tools ntfy_me and ntfy_me_fetch appear in the client's tool list, then ask it to send a test notification and check it arrives on your device subscribed to NTFY_TOPIC.

Troubleshooting

  1. If you don't receive notifications, check your NTFY_TOPIC and NTFY_URL settings.
  2. For protected topics, ensure NTFY_TOKEN is set.
  3. Test connectivity: curl -d "test" ntfy.sh/your-topic.
  4. If using Docker, ensure environment variables are passed correctly.

Things to try

Once connected, you can ask your AI assistant things like:

  • Send me a notification when the build is complete
  • Notify me with a high priority alert titled 'Code Generation Complete' when the task is done
  • Show me my recent notifications from the last hour
  • Find notifications with the title 'Build Complete' from the last 24 hours

Tools 2

ntfy_me writes
Send a notification to a specified ntfy topic with title, message, priority, tags, markdown, and actions.
ntfy_me_fetch read-only
Fetch and filter cached messages from ntfy topics, with filters by time, ID, text, title, priority, and tags.

Use cases

Notify on AI task completion
Fetch and filter recent notifications
Send real-time alerts to phone/desktop
Send notifications on self-hosted ntfy servers

Supported clients

Claude Desktop
VS Code
OpenCode
GitHub Copilot CLI

Listed from the project's documentation, not tested by this site.

Overview

ntfy-me-mcp is a Model Context Protocol (MCP) server that enables AI assistants to send real-time notifications via the ntfy service (public or self-hosted with token support). It supports rich notifications with topics, titles, priorities, tags, and detailed messages, along with smart features like automatic URL detection for view actions and intelligent markdown formatting detection. The server can be quickly set up via npx or Docker.

Similar servers

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →
Compare with other MCP servers

Source revision 63598a9f2b64 Data synced 2026-10-12 Read the FMRS scoring method