MCPHub is a self-hosted gateway that connects and manages multiple MCP servers, which provide tools, prompts, and resources to AI applications. Users organize servers into groups, control access, monitor activity and health, and expose stable endpoints to clients such as Claude Code, Cursor, and OpenWebUI; the catalogue entries operate within this MCP environment.
Borrowing it
Nothing to install: this file belongs to samanhappy/mcphub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/samanhappy/mcphub/main/AGENTS.mdgit clone --depth 1 https://github.com/samanhappy/mcphubWrote 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/samanhappy/mcphub/agents-md)<a href="https://agentmods.dev/instructions/samanhappy/mcphub/agents-md"><img src="https://agentmods.dev/badge/instructions/samanhappy/mcphub/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/samanhappy/mcphub/agents-md"><img src="https://agentmods.dev/badge/instructions/samanhappy/mcphub/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00599 | $0.00599 |
| Opus 5.5 | $0.00240 | $0.00240 |
| Sonnet 5.5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
mcphub 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- xiaozhi-mcphub AGENTS.md — 95% identical, 221 lines differ
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCPHub — Agent Guide
MCPHub (@samanhappy/mcphub) is a TypeScript/Node.js ESM hub that aggregates MCP servers behind a single HTTP service with a React/Vite dashboard.
Always apply
- Use
pnpm([email protected], declared inpackage.json). - Treat the current implementation as the source of truth. If this guide disagrees with the code, follow the code and update the guide; tests document expected behavior and should change only when behavior intentionally changes.
- Do not hand-edit generated output:
dist/,frontend/dist/, orcoverage/. - Read the scoped guide relevant to the files you will change. The full index is in docs/agents/README.md.
- Prefer the
ghCLI for GitHub operations — reviewing PRs, reading issues, fetching diffs, creating PRs — over scraping the GitHub web UI or hand-calling the REST API. Command details live in docs/agents/git-and-contribution.md. - The agent shell runs non-interactively with a minimal
PATH, so baregh,pnpm,node, andnpxmay reportcommand not foundeven when installed. See docs/agents/development.md ("Agent shellPATH") for how to locate and export the toolchain. - The agent shell file sandbox denies writes outside the repo, so
npx/uvxcache writes fail withEPERMand tests that spawn real MCP servers vianpxtime out. See docs/agents/development.md ("Agent shell file sandbox") for the workaround.
Project-specific build checks
- Backend typecheck/build:
pnpm backend:build - Full build:
pnpm build - Distribution verification:
node scripts/verify-dist.js - Mintlify docs validation:
pnpm docs:validate
Scoped guides
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.
- 1mo ago Changed · +2 lines · +86 tokens per session 86c702217165
- 1mo ago Changed · +1 lines · +75 tokens per session 90c1f0440110
- 1mo ago Changed · +1 lines · +13 tokens per session 58095c6cd38d
- 1mo ago Changed · +1 lines · +65 tokens per session 203d531a4d73
- 1mo ago Changed · -172 lines · -2,399 tokens per session 98436bca0f11
- 2mo ago First seen · 202 lines · 2,759 tokens per session scan A 52927fd0ba5b
mcphub AGENTS.md is an instructions file published in the GitHub repository samanhappy/mcphub (2,600 stars, last pushed today), licensed Apache-2.0. It adds 599 tokens to every session, about $0.0024 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.