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/my-mcp-hub/node-mcp-server/agents-mdgit clone --depth 1 https://github.com/my-mcp-hub/node-mcp-serverWrote 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/my-mcp-hub/node-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/my-mcp-hub/node-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/my-mcp-hub/node-mcp-server/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 | $0.00649 | $0.00649 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
node-mcp-server 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository guide
Toolchain and verification
- Use Node 22 (
.nvmrc) and npm 10;package-lock.jsonis the dependency source of truth. Usenpm cifor a clean install. npm run checkmatches CI's lint, build, coverage sequence; build itself runs type-check, esbuild, thentsc-alias.- Run one test file with
npx vitest run tests/tools/index.test.ts; add-t 'test name'for one case. npm run dev:stdioandnpm run dev:webwatch the source and start MCP Inspector. The web endpoint ishttp://localhost:8401/mcp.npm pack --dry-runvalidates the publish allowlist and triggers a fresh production build; CI uses--ignore-scriptsonly because it builds first.
Architecture and invariants
src/index.tsis the CLI entrypoint. Omitting the command starts stdio;stdiois also accepted explicitly, whilewebselects Streamable HTTP. Onlywebaccepts--port; it andPORTmust resolve to an integer from 1 to 65535.- Production builds preserve every
src/**/*.tsmodule underbuildwithbundle: false;tsc-aliasrewrites@/imports and adds Node ESM.jssuffixes. Keepscripts/aliasReplacer.cjs,tsconfig.json, and the esbuild output layout synchronized. src/services/index.ts#createServeris the shared server factory. Register tools, resources, and prompts through theirsrcregistrars so both transports expose the same behavior.- The HTTP transport uses Fastify; Express middleware and lifecycle patterns do not apply.
src/data/documents.tsis the single built-in knowledge-base source; record changes affect tool ranking, resource URIs/listing, prompt completion, and their tests.- The server and tests pin MCP protocol
2026-07-28. Avoid session-ID-dependent behavior because the HTTP handler creates independent server instances. - Tools with an
outputSchemamust return matchingstructuredContentand a text fallback.
Test and runtime gotchas
- Vitest global setup launches a real web server and setup launches a real stdio child; transport tests iterate over both clients.
- Even a focused test starts HTTP on port 8401. Stop
dev:webor any other listener first, and keep Vitest at one worker because the shared port and global clients are not parallel-safe. - Never write ordinary logs to stdout on the stdio path; stdout carries MCP protocol messages.
src/assets/mcp.stdio.jsonandsrc/assets/mcp.http.jsonconfigure Inspector launch targets.
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 · 32 lines · 649 tokens per session scan A e158159ee298
node-mcp-server AGENTS.md is an instructions file published in the GitHub repository my-mcp-hub/node-mcp-server (2 stars, last pushed 5d ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.