About rakuten-japan-mcp
rakuten-japan-mcp provides access to Rakuten Ichiba product searches and rankings through official Rakuten APIs. It serves MCP clients and can also run as an Apify actor.
Key features
- 01Keyword-based product search
- 02Current product rankings
- 03Genre and ranking-type filters
- 04Historical ranking queries
- 05Structured product details
Use cases
- 01Find Rakuten products by keyword
- 02Check current rankings by genre
- 03Review past rankings for a date
MCP support
Exposes `search_rakuten`, `search_rakuten_ranking` and `get_actor_info` tools to MCP clients through the actor's standby endpoint.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERakuten Japan MCP — 楽天市場商品検索・ランキング
Search Rakuten Ichiba (楽天市場) products and fetch the current ranking via the official Rakuten APIs.
Extract item names, prices, URLs, shop info, reviews, and images in clean structured JSON.
🚀 What This Does
This actor wraps the official Rakuten APIs and makes them available two ways:
- A traditional Apify actor — run it from the Apify Console, API, or schedule
- An MCP server — connect AI agents (Claude, Cursor, ChatGPT) to query Rakuten in real-time
Two data access modes:
- Product search —
IchibaItem/Searchofficial API (keyword search) - Ranking —
IchibaItem/Rankingofficial API (what's hot, genre ranking, historical eras)
Why use this? Rakuten is Japan's largest e-commerce platform with millions of products. This actor gives you programmatic access to product and ranking data without scraping HTML or managing proxies — both via TOS-compliant official APIs.
🔧 Usage
As an Apify Actor
1. Product Search — set searchKeyword (e.g. "ポケモン", "フィギュア", "PS5") and optional filters.
2. Ranking — set ranking to true, optionally narrow with genreId:
| Parameter | Type | Default | Description |
|---|---|---|---|
ranking | boolean | false | Set true to fetch ranking instead of search |
genreId | integer | — | Restrict to genre (e.g. 101269=本・雑誌, 101347=おもちゃ) |
rankingType | select | item | item, male, or female |
era | string | — | Past-ranking era YYYYMMDD (e.g. 20190601) |
maxResults | int | 30 | Max results (ranking max 30 per call) |
As an MCP Server
Connect any MCP-compatible client to the actor's standby endpoint.
Tools:
search_rakuten— keyword product search, returns title/price/URL/shop/review/imagesearch_rakuten_ranking— current Rakuten ranking (genre / male / female / historical era)get_actor_info— list of tools and pricing
🧹 Official API Details
- Search:
https://openapi.rakuten.co.jp/ichibams/api/IchibaItem/Search/20260701 - Ranking:
https://app.rakuten.co.jp/services/api/IchibaRanking/Ranking/20220601
Search requires RAKUTEN_APP_ID and RAKUTEN_ACCESS_KEY; ranking requires only RAKUTEN_APP_ID. These are Secret environment variables set on the Apify actor.
🧪 Tests & Type Checking
python -m pytest tests/ -v
python -m mypy src/ --strict
Deploy happens automatically on push to master/main via GitHub Actions.
🔒 Pricing (pay-per-event)
rakuten-search: $0.001 / searchrakuten-ranking: $0.001 / ranking
MCP Registry
This server is registered on the official MCP Registry. Find it via search: rakuten-japan-mcp
Data & Store
- Apify Store: https://apify.com/fruitful_quintessence
- Gumroad datasets: https://atushi5.gumroad.com/l/kutuxe
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.