Rakuten MCP server for AI agents
Let Claude, ChatGPT or your own agent read Rakuten: 2 typed functions through one MCP server. No Rakuten API key needed.
- Site
- rakuten.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Rakuten
An MCP server for Rakuten alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/rakutenEvery site
One MCP server for Rakuten and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getStoreReads one Rakuten store page.Arguments
Name Type Required refstringYes Returns
RakutenStoreDetailinterface RakutenStoreDetail { slug: string; name: string; cashBack: string | null; headline: string | null; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/rakuten/getStoreCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.rakuten.getStore("<ref>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.rakuten.getStore("<ref>"))curl -X POST https://api.bowmark.ai/v1/sites/rakuten/getStore \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"ref":"<ref>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.rakuten.getStore("<ref>");searchSearches Rakuten's cash-back store directory by store or brand name the way its search box does, returning each store's current cash-back rate, offer…Arguments
Name Type Required querystringYes limitnumber1-50, default 10.No Returns
RakutenSearchResultinterface RakutenStore { storeId: string; name: string; /** Path slug, what getStore takes. */ slug: string; /** "8.0%", "Up to 3.0%", "$10.00" or "No Discount". */ cashBack: string; /** e.g. "8.0% Cash Back". */ offer: string; logoUrl: string | null; url: string; } interface RakutenSearchResult { query: string; totalCount: number | null; stores: RakutenStore[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/rakuten/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.rakuten.search({ query: "macys" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.rakuten.search({"query": "macys"}))curl -X POST https://api.bowmark.ai/v1/sites/rakuten/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"macys"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.rakuten.search({ query: "macys" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/rakuten/<function> - OpenAPI
/v1/sites/rakuten/openapi.json