01-mdn-mcp-tools

01-mdn-mcp-tools is a cursor rule for Cursor from gurezo/mdn-translation-ja-mcp. It costs 615 tokens per session, scanned A, original, MIT.

A set of rules for calling MDN translation tools through an MCP connection, a standard way for AI assistants to use external tools. It specifies the allowed tool names, inputs, and fallback command.

In plain words
What is it for?
It helps review MDN Japanese translation files, start or commit translation work, replace glossary terms, and report review results.
Why use it?
It prevents the assistant from mistakenly trying to run these tools as shell commands or edit translation files after a read-only review.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit It helps review MDN Japanese translation files, start or commit translation work, replace glossary terms, and report review results.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools
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/gurezo/mdn-translation-ja-mcp

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 01-mdn-mcp-tools

README.md
[![agentmods](https://agentmods.dev/badge/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools/github.svg)](https://agentmods.dev/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools)
Your own site
<a href="https://agentmods.dev/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools"><img src="https://agentmods.dev/badge/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools/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 01-mdn-mcp-tools

Your own site · 80×15
<a href="https://agentmods.dev/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools"><img src="https://agentmods.dev/badge/rules/gurezo/mdn-translation-ja-mcp/01-mdn-mcp-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 615 This file is loaded in full into every session.
When invoked 615 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 $0.00615 $0.00615
Opus 5 $0.00308 $0.00308
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00061 $0.00061

Measured 7d ago against content hash 60cf28c0e115, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

01-mdn-mcp-tools 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 7d 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/01-mdn-mcp-tools.mdc · 42 lines

What it actually says

MDN 翻訳 MCP ツール — 呼び出し制約

必須

mdn_trans_start / mdn_trans_commit_get / mdn_trans_replace_glossary / mdn_trans_reviewシェルコマンド・npm スクリプト・CLI ではない

  • 禁止: ターミナルで mdn_trans_review 等を実行しようとすること
  • 禁止: リポジトリ内に同名のシェルスクリプトを探して代替実行すること
  • 必須: Cursor の MCP ツールとして呼び出す(サーバー名: mdn-translation-ja、ツール名: 上記のスネークケース名)

mdn_trans_review の引数

引数 説明
jaFile translated-content 内のパス(files/ja/.../index.md または絶対パス)

ユーザーが「mdn_trans_review を実行して」と依頼した場合は、MCP ツール mdn_trans_reviewjaFile 付きで呼び出し、返却テキストをそのまま報告する。

MCP ツールが利用できない場合のみ、mdn-translation-ja-mcp リポジトリで次を実行する(npm start ではない):

npm run mdn:trans:review -- --jaFile=files/ja/.../index.md

MDN_CONTENT_ROOT / MDN_TRANSLATED_CONTENT_ROOT が設定されていること)

それ以外は node scripts/setup-translated-content-cursor.mjstranslated-content/.cursor/mcp.json を生成し、Cursor をリロードするよう案内する。Rules / Skills のコピーは不要(任意の薄い Rule は --with-rules)。

標準手順は MCP Prompt(mdn_translate / mdn_sync / mdn_review)を使う。

読み取り専用

mdn_trans_review の結果を理由に、対象 index.md を編集・保存しない(ユーザーが明示的に修正を依頼した場合のみ可)。

translated-content ワークスペース

ワークスペースが translated-content のときも同じ。MCP は translated-content/.cursor/mcp.json で接続する(mdn-translation-ja-mcp を開いている必要はない)。

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. 7d ago Changed · +2 lines · +52 tokens per session 60cf28c0e115
  2. 10d ago First seen · 40 lines · 563 tokens per session scan A d59ff9b73cb9

Subscribe to this mod's changes

01-mdn-mcp-tools is a cursor rule published in the GitHub repository gurezo/mdn-translation-ja-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 615 tokens to every session, about $0.0031 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.