Williams Sonoma MCP server for AI agents
Let Claude, ChatGPT or your own agent read Williams Sonoma: 1 typed function through one MCP server. No Williams Sonoma API key needed.
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Williams Sonoma
An MCP server for Williams Sonoma 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/williams_sonomaEvery site
One MCP server for Williams Sonoma 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
searchProductsSearches the Williams Sonoma catalog the way its own search box does ("stand mixer") and returns products with current and regular price, the price…Arguments
Name Type Required querystringWhat the store's own search box takes, e.g. "stand mixer".Yes sort"relevance" | "price_ascending" | "price_descending"No pagenumberFrom 1.No limitnumber1-100, default 24.No Returns
WsgcSearchinterface WsgcProduct { id: string; // the store's product slug name: string; url: string; // the product page price: number | null; // lowest current price across its sizes/colours, USD maxPrice: number | null; // highest current price, a range when it differs from price regularPrice: number | null; // lowest regular (non-sale) price maxRegularPrice: number | null; onSale: boolean; priceType: string | null; // the store's own word: "Regular", "Discount", "Clearance" maxDiscountPercent: number | null; description: string; imageUrl: string | null; flags: string[]; // the store's badges, e.g. "freeShip", "bestseller" } interface WsgcSearch { products: WsgcProduct[]; total: number; // matches across all pages page: number; // Set when the store maps this term to a category page instead of searching it; the // products then come from the store's own autocomplete and there is no next page. redirect: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/williams_sonoma/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.williams_sonoma.searchProducts({ query: "stand mixer", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.williams_sonoma.searchProducts({"query": "stand mixer", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/williams_sonoma/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"stand mixer","limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.williams_sonoma.searchProducts({ query: "stand mixer", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/williams_sonoma/<function> - OpenAPI
/v1/sites/williams_sonoma/openapi.json