Cdiscount MCP server for AI agents
Let Claude, ChatGPT or your own agent read Cdiscount: 1 typed function through one MCP server. No Cdiscount API key needed.
- Site
- cdiscount.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Cdiscount
An MCP server for Cdiscount 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/cdiscountEvery site
One MCP server for Cdiscount 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 1
searchSearch cdiscount.com for products by name (the /search/10/<query>.html results page) one page at a time (page), and return each result's title, euro…Arguments
Name Type Required querystringYes pagenumber1-based results page, default 1 (~50 rows a page).No Returns
CdiscountSearchPageinterface CdiscountSearchPage { results: CdiscountSearchResult[]; /** the site's own "Résultats : N produits" count */ total: number | null; page: number; pageCount: number | null; returned: number; /** says when this page is partial (returned < total) and how many rows are accessories */ warnings: string[]; } interface CdiscountSearchResult { productId: string; title: string; url: string; image: string | null; price: number | null; currency: "EUR"; rating: number | null; reviewCount: number; /** an accessory FOR a product (earpads, case, cable…) the query did not ask for */ accessory: boolean; /** every query word is in the title and it is not an accessory, cdiscount's search is fuzzy */ matchesQuery: boolean; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/cdiscount/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.cdiscount.search({ query: "JBL Tune 510BT" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.cdiscount.search({"query": "JBL Tune 510BT"}))curl -X POST https://api.bowmark.ai/v1/sites/cdiscount/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"JBL Tune 510BT"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.cdiscount.search({ query: "JBL Tune 510BT" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/cdiscount/<function> - OpenAPI
/v1/sites/cdiscount/openapi.json