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/apitube/news-api-mcp/agents-mdgit clone --depth 1 https://github.com/apitube/news-api-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/apitube/news-api-mcp/agents-md)<a href="https://agentmods.dev/instructions/apitube/news-api-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/apitube/news-api-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 | $0.00879 | $0.00879 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
news-api-mcp AGENTS.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://mcp.apitube.io/ -H 'Content-Type: application/json' \ How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repository.
What this repository is
Documentation and client configs for the hosted APITube News MCP server at
https://mcp.apitube.io/. The server itself is not here — it runs as a service, and this repository
is what a user or an agent reads to connect to it.
README.md what the server is, how to connect, what the tools accept
llms-install.md install instructions written for an agent doing the setup
server.json the entry published to registry.modelcontextprotocol.io
configs/ ready config files, one per MCP client
assets/logo.svg APITube logo at the top of the README (light theme)
assets/logo-dark.svg white version for prefers-color-scheme: dark
assets/logo-400.png 400×400 icon for directories that ask for one
There is no build step, no dependencies and no server code.
Rules for editing
-
Verify against the running server before writing anything down.
initialize,tools/listandprompts/listanswer without a key:curl -s -X POST https://mcp.apitube.io/ -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'Tool arguments, defaults and limits come from the live
tools/listschema, not from memory. -
Do not trust the docs over the server. Where https://docs.apitube.io and the running service disagree, the service wins and this repository records the real behaviour.
-
Never put a real API key in an example. Use
YOUR_API_KEYin configs and readAPITUBE_API_KEYfrom the environment in scripts. -
Every config here must be pasteable as-is. Test a changed config in the client it targets before committing it — a key in the wrong header fails as
401 ER0201with no other hint. -
server.jsonmirrors the published registry entry (io.apitube/news). Changing it here does not publish anything — the entry is published separately withmcp-publisher, and a change to tools or transport means bumpingversionin both places.
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.
- 4d ago First seen · 73 lines · 879 tokens per session scan A 48bfb6569538
news-api-mcp AGENTS.md is an instructions file published in the GitHub repository apitube/news-api-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 879 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
easy-notion-mcp CLAUDE.md
Claude Code instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
pyobfus CLAUDE.md
Claude Code instructions for zhurong2020/pyobfus, covering pyobfus 开发约定, ⚡ current pending work (cold-start 必读), 🟢 2026-09-04 — core 0.5.21 已发布后的当前焦点, ✅ 2026-09-02 — seo 小版本全渠道发布收口 and ✅ 2026-08-24 — 0.5.17 / mcp 0.3.8 发布与外部渠道收尾.
pyobfus AGENTS.md
AGENTS.md instructions for zhurong2020/pyobfus, covering agents.md — pyobfus, what this project is, setup, build / test / lint — run before every commit and self-dogfooding boundary.
agentshare-mcp AGENTS.md
AGENTS.md instructions for anhmtk/agentshare-mcp, covering agentshare — briefing for ai agents (agents.md), when to select agentshare, fetch order (machine), mcp (production) and tools (12).
weeek-mcp CLAUDE.md
Claude Code instructions for YOLKINS/weeek-mcp, covering claude.md — guide for ai coding agents working on weeek-mcp, what this is, tech stack pinning, mcp invariants (do not break — even temporarily) and logging discipline.
overleaf-mcp-rt CLAUDE.md
Claude Code instructions for DanielHou315/overleaf-mcp-rt, covering overleaf-mcp-rt, source of truth, status, hard constraints and tech stack.