Borrowing it
Nothing to install: this file belongs to mrslbt/rakuten-mcp. 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/mrslbt/rakuten-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/mrslbt/rakuten-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/mrslbt/rakuten-mcp/agents-md)<a href="https://agentmods.dev/instructions/mrslbt/rakuten-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/rakuten-mcp/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/mrslbt/rakuten-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mrslbt/rakuten-mcp/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 | $0.04094 | $0.04094 |
| Opus 5 | $0.02047 | $0.02047 |
| Sonnet 5 | $0.00819 | $0.00819 |
| Haiku 4.5 | $0.00409 | $0.00409 |
Grade A, and why
rakuten-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 9d 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.
The plan documents and third-party API surveys lie. Endpoints get silently moved, dates get bumped, response shapes change. The pattern is: probe with `curl` + your real `RAKUTEN_APP_ID`, watch the response shape, then w How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — rakuten-mcp
Instructions for AI coding agents (Codex, Cursor, Copilot, Claude Code, etc.) contributing to this repository.
What this project is
rakuten-mcp is a Model Context Protocol server that exposes the public Rakuten Web Service as MCP tools. It is read-only — there are no money-moving operations, no merchant-side (RMS) endpoints, no destructive actions. Distribution: npm (rakuten-mcp), listed in the Official MCP Registry as io.github.mrslbt/rakuten-mcp, plus Glama / Smithery / mcp.so / Cline marketplace / PulseMCP / LobeHub / awesome-mcp-servers.
28 tools across 6 API families (as of v1.0.0, verified live on 2026-06-04):
| Family | Prefix | Tools | Host | Path root |
|---|---|---|---|---|
| Ichiba (e-commerce) | ichiba_* |
5 | openapi.rakuten.co.jp |
/ichibams/api/, /ichibagt/api/, /ichibaranking/api/, /ichibaproduct/api/ |
| Books | books_* |
9 | openapi.rakuten.co.jp |
/services/api/ |
| Travel (hotels) | travel_* |
7 | openapi.rakuten.co.jp |
/engine/api/Travel/ |
| Recipe | recipe_* |
2 | openapi.rakuten.co.jp |
/recipems/api/ |
| Kobo (eBooks) | kobo_* |
2 | openapi.rakuten.co.jp |
/services/api/Kobo/ |
| GORA (golf) | gora_* |
3 | openapi.rakuten.co.jp |
/engine/api/Gora/ |
Everything is on openapi.rakuten.co.jp now. The pre-migration app.rakuten.co.jp host is no longer used by any shipped tool. The constant HOST_LEGACY still exists in src/config.ts as documentation of the old host, but no tool imports it. What varies per endpoint is the path root, not the host. Within Ichiba alone there are four distinct path roots.
This is the result of Rakuten's 2026-04 platform migration. The host moved, the path roots fragmented, and the version date on each endpoint may or may not have bumped. Three Ichiba response shapes were also rewritten in that migration (genre is now flat ancestors/siblings/children, tag is tagId-only, product uses productId opaque hash).
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.
- 9d ago First seen · 290 lines · 4,094 tokens per session scan A 953a805e542d
rakuten-mcp AGENTS.md is an instructions file published in the GitHub repository mrslbt/rakuten-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 4,094 tokens to every session, about $0.0205 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.