QVC MCP server for AI agents
Let Claude, ChatGPT or your own agent read QVC: 2 typed functions through one MCP server. No QVC API key needed.
- Site
- qvc.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just QVC
An MCP server for QVC 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/qvcEvery site
One MCP server for QVC 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
getProductReads one QVC product by item number or qvc.com URL: current and QVC price, sale badge, rating, stock, shipping, payment plan, variants, description…Arguments
Name Type Required productNumberstringYes Returns
qvcProductinterface qvcProductSummary { productNumber: string; title: string; brand: string | null; price: number | null; qvcPrice: number | null; priceBadge: string | null; rating: number | null; reviewCount: number | null; inStock: boolean; imageUrl: string | null; url: string; } interface qvcProductVariant { itemNumber: string; colorCode: string | null; sizeCode: string | null; price: number | null; inStock: boolean; } interface qvcProduct extends qvcProductSummary { description: string | null; currency: string | null; installments: string | null; shippingCharge: number | null; variants: qvcProductVariant[]; attachments: { title: string; url: string }[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/qvc/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.qvc.getProduct({ productNumber: "K46588" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.qvc.getProduct({"productNumber": "K46588"}))curl -X POST https://api.bowmark.ai/v1/sites/qvc/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"productNumber":"K46588"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.qvc.getProduct({ productNumber: "K46588" });searchProductsSearches the QVC shopping catalog by keyword and returns item number, title, price, sale badge, rating, stock, image and product URL.Arguments
Name Type Required querystringYes limitnumberNo offsetnumberNo Returns
qvcSearchResultinterface qvcProductSummary { productNumber: string; title: string; brand: string | null; price: number | null; qvcPrice: number | null; priceBadge: string | null; rating: number | null; reviewCount: number | null; inStock: boolean; imageUrl: string | null; url: string; } interface qvcSearchResult { query: string; total: number; offset: number; products: qvcProductSummary[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/qvc/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.qvc.searchProducts({ query: "blender", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.qvc.searchProducts({"query": "blender", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/qvc/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"blender","limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.qvc.searchProducts({ query: "blender", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/qvc/<function> - OpenAPI
/v1/sites/qvc/openapi.json