Best Buy MCP server for AI agents
Let Claude, ChatGPT or your own agent read Best Buy: 2 typed functions through one MCP server. No Best Buy API key needed.
- Site
- bestbuy.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Best Buy
An MCP server for Best Buy 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/bestbuyEvery site
One MCP server for Best Buy 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
getProductLooks up one product by Best Buy's own numeric SKU and returns its full detail.Arguments
Name Type Required skustring | numberYes Returns
bestbuyProductinterface bestbuyProduct { sku: number; name: string; salePrice: number | null; regularPrice: number | null; url: string | null; imageUrl: string | null; onlineAvailability: boolean; inStoreAvailability: boolean; manufacturer: string | null; modelNumber: string | null; upc: string | null; customerReviewAverage: number | null; customerReviewCount: number | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bestbuy/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bestbuy.getProduct(6418599);import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bestbuy.getProduct(6418599))curl -X POST https://api.bowmark.ai/v1/sites/bestbuy/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"sku":6418599}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.bestbuy.getProduct(6418599);searchRuns a Best Buy product search the way bestbuy.com's own search box does and returns matching products.Arguments
Name Type Required argsstring | { query: string; pageSize?: number }Yes Returns
bestbuyProduct[]interface bestbuyProduct { sku: number; name: string; salePrice: number | null; regularPrice: number | null; url: string | null; imageUrl: string | null; onlineAvailability: boolean; inStoreAvailability: boolean; manufacturer: string | null; modelNumber: string | null; upc: string | null; customerReviewAverage: number | null; customerReviewCount: number | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bestbuy/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bestbuy.search({ query: "laptop" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bestbuy.search({"query": "laptop"}))curl -X POST https://api.bowmark.ai/v1/sites/bestbuy/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"laptop"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.bestbuy.search({ query: "laptop" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/bestbuy/<function> - OpenAPI
/v1/sites/bestbuy/openapi.json