mcp-hub-core

mcp-hub-core is a cursor rule for Cursor from ONE8943/ai-furniture-hub. It costs 1,123 tokens per session, scanned A, original, MIT.

A set of project rules for an MCP hub, a program that lets AI agents use connected tools for furniture, appliances, and gadgets. The rules cover safe handling of secrets, privacy, affiliate links, and documentation.

In plain words
What is it for?
Use it when changing the hub, its tools, its public descriptions, affiliate integrations, or privacy-related logging.
Why use it?
It prevents sensitive values and misleading claims from entering code, logs, or public pages, while keeping tool documentation aligned with the implementation.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions AGENTS.md.

Good fit Use it when changing the hub, its tools, its public descriptions, affiliate integrations, or privacy-related logging.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/one8943/ai-furniture-hub/mcp-hub-core
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ONE8943/ai-furniture-hub

Made for: Cursor.

Wrote 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.

agentmods badge for mcp-hub-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/one8943/ai-furniture-hub/mcp-hub-core/github.svg)](https://agentmods.dev/rules/one8943/ai-furniture-hub/mcp-hub-core)
Your own site
<a href="https://agentmods.dev/rules/one8943/ai-furniture-hub/mcp-hub-core"><img src="https://agentmods.dev/badge/rules/one8943/ai-furniture-hub/mcp-hub-core/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.

agentmods 80×15 button for mcp-hub-core

Your own site · 80×15
<a href="https://agentmods.dev/rules/one8943/ai-furniture-hub/mcp-hub-core"><img src="https://agentmods.dev/badge/rules/one8943/ai-furniture-hub/mcp-hub-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,123 This file is loaded in full into every session.
When invoked 1,123 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01123 $0.01123
Opus 5 $0.00562 $0.00562
Sonnet 5 $0.00225 $0.00225
Haiku 4.5 $0.00112 $0.00112

Measured 12d ago against content hash 20e10c214196, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-hub-core 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 12d 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.

.cursor/rules/mcp-hub-core.mdc · 64 lines

What it actually says

MCP Hub コアルール

このプロジェクトは家具・家電・ガジェット等のAIエージェント向けMCPハブ。 rules/*.md はタスクに必要なものだけ読む(毎回すべてを開かない)。全体像はルート AGENTS.md、ツールの使い方の詳細は public/AGENTS.md。カタログ件数・ツール数など断定値はコードで確認すること。

🚨 情報漏洩防止(絶対最優先 — 全ルールに優先する)

以下に違反した場合、他の全作業を即座に中止して修正すること。

禁止事項

  • APIキー・シークレット・トークンをソースコードやコメントに直書き禁止(.envのみ許可)
  • アフィリエイトID・APIキーの実際の値をコメント・ドキュメント・テストコード・ログ例に記載禁止
  • IPアドレス・個人名をソースコード・ドキュメントに記載禁止
  • .env.exampleには your_xxx_herexxxxxxxx 等のダミー値のみ使用すること

コミット前チェック(必須)

  1. git diff --cached で以下のパターンが含まれていないことを確認:
    • APIキーの実値(英数字+ハイフンの長い文字列)
    • アフィリエイトIDの実値(ドット区切りのHEX文字列)
    • AIzaSy で始まる文字列(Google APIキー)
    • pk_ / sk_ で始まる文字列(各種APIキー)
    • IPアドレス(xxx.xxx.xxx.xxx 形式)
  2. 新規ファイル・ドキュメント更新時は必ず上記パターンでgrepし、漏洩がないことを確認すること

万が一漏洩した場合

  1. 即座にファイルから除去(<REDACTED> に置換)
  2. 原本は .secrets_backup/ に隔離(.gitignore 済み)
  3. 漏洩したキーは必ず再発行(旧キーは無効化)
  4. Git履歴に残っている場合は BFG Repo-Cleaner 等で除去を検討

コンプライアンス(最優先)

違反はリリースブロッカー。細目は rules/affiliate.md(Amazon/楽天・JSON-LD・公開文言)、rules/privacy.md(intent・ログ種別・インフラログの書き方)。

  • アフィリエイト: フッター開示・実態と異なる表現禁止・価格注記。Amazon は URL 生成のみ等。
  • JSON-LD: 虚偽の評価・件数の断定禁止。ページ上の可視テキストと整合。
  • プライバシー: 「個人情報を一切収集しない」とは断言しない。
  • ドキュメント: ツール説明は実装と一致。公開ファイル間で表現を揃える。

開発ルール

  1. 全MCPツールに intent 引数を含めること → rules/insight-collection.md
  2. 全検索結果を logs/analytics.jsonl に記録すること → rules/logging.md
  3. 個人情報を意図的に記録しないこと → rules/privacy.md
  4. サイズはmm単位、価格は円(整数)で統一 → rules/typescript.md
  5. 外部入力は必ずZodでバリデーションすること → rules/typescript.md
  6. 付加価値・実使用改善・通販外データの方針 → rules/mcp-value-iteration.md(レスポンスに次ツール案 recommended_follow_up を含めること)

モード別ルール

  • 実装モード: 上記5項を遵守してコーディング
  • 情報収集モード: .cursor/rules/research-mode.mdc を使用(コード変更不可)
  • 役割分担: rules/model-routing.md を参照

Cursor / Composer

  • このリポジトリを開いているときはルート AGENTS.md を最初のコンテキストに使う。
  • 別アプリのフォルダ(別リポジトリ)を同じワークスペースに混ぜるとルールとコードが噛み合わない。フォルダ単位で開き直すと安定する。
Changes

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.

  1. 12d ago First seen · 64 lines · 1,123 tokens per session scan A 20e10c214196

Subscribe to this mod's changes

mcp-hub-core is a cursor rule published in the GitHub repository ONE8943/ai-furniture-hub (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,123 tokens to every session, about $0.0056 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.