Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/tadmstr/ntfy-mcp/agents-mdgit clone --depth 1 https://github.com/TadMSTR/ntfy-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/tadmstr/ntfy-mcp/agents-md)<a href="https://agentmods.dev/instructions/tadmstr/ntfy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tadmstr/ntfy-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00307 | $0.00307 |
| Opus 5 | $0.00153 | $0.00153 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
ntfy-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
ntfy-mcp
FastMCP server for ntfy push notifications. Single write-only tool.
What it does
Publishes notifications to an ntfy server (self-hosted or ntfy.sh) with support for title, priority, tags, Markdown, click URL, and icon.
Tools
send_notification(message, topic?, title?, priority?, tags?, markdown?, click?, icon?)— Publishes to the configured ntfy server. UsesNTFY_DEFAULT_TOPICif no topic is provided.
Structure
src/
__init__.py
server.py FastMCP server — exposes send_notification tool
tools/
notifications.py send_notification_handler() — httpx POST to ntfy
tests/ pytest tests
requirements.txt
requirements-dev.txt
Configuration
| Env var | Default | Purpose |
|---|---|---|
NTFY_URL |
(required) | ntfy server base URL (e.g. https://ntfy.sh) |
NTFY_DEFAULT_TOPIC |
— | Default publish topic |
NTFY_TOKEN |
— | Auth token for private topics |
MCP_PORT |
8484 |
MCP server port |
Testing
pip install -r requirements-dev.txt
pytest
Git workflow
Branch before editing — do not commit directly to main.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 45 lines · 307 tokens per session scan A 0f54093ac6fe
ntfy-mcp AGENTS.md is an instructions file published in the GitHub repository TadMSTR/ntfy-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 307 tokens to every session, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ntfy-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
agent-inbox CLAUDE.md
Claude Code instructions for Ideaplaces/agent-inbox, covering agent inbox: working notes, local development, gotchas already paid for, keep readme.md current and conventions.
claude-usage-tray-windows AGENTS.md
AGENTS.md instructions for jeiel85/claude-usage-tray-windows, covering claude usage tray windows — agent rules, ⚠️ 작업 전 필수 확인 사항, 최신 소스 동기화 및 상태 확인, 📋 핵심 개발 규칙 and 0. 이슈 기반 개발.
ntfy-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/ntfy-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
ntfy-me-mcp copilot-instructions.md
Copilot instructions for gitmotion/ntfy-me-mcp, covering project guidelines, build and test, architecture, conventions and security and validation.
claude-usage-tray-windows GEMINI.md
Gemini CLI instructions for jeiel85/claude-usage-tray-windows: 이 파일은 Gemini CLI 에이전트를 위한 진입점입니다. 모든 핵심 가이드라인과 규칙은 AGENTS.md에 통합되어 관리됩니다.