Bob's Discount Furniture MCP server for AI agents
Let Claude, ChatGPT or your own agent read Bob's Discount Furniture: 1 typed function through one MCP server. No Bob's Discount Furniture API key needed.
- Site
- mybobs.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Bob's Discount Furniture
An MCP server for Bob's Discount Furniture 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/bobsEvery site
One MCP server for Bob's Discount Furniture 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 Bob's Discount Furniture catalog the way its own search box does ("sofa") and returns products with current price, outlet flag, summary…Arguments
Name Type Required querystringWhat the store's own search box takes, e.g. "sofa".Yes sort"relevance" | "price_ascending" | "price_descending" | "newest" | "rating"No pagenumberFrom 1; each page is 100 rows of the store's index.No limitnumber1-100, default 24; the most rows returned from that page.No Returns
BobsSearchinterface BobsProduct { sku: string; // the store's product code name: string; // e.g. "Aspen Forest 78'' Sofa" url: string; // the product page on www.mybobs.com price: number | null; // current price, USD maxPrice: number | null; // top of the range when the product has one, else = price formattedPrice: string | null; // as the store prints it, "$399.00" outlet: boolean; // an outlet (clearance) item summary: string; imageUrl: string | null; } interface BobsSearch { products: BobsProduct[]; // the store's haul-away service rows are left out total: number; // matches across all pages page: number; totalPages: number; // pages of 100 index rows categoryUrl: string | null; // the category page the store maps this term to, when it does }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/bobs/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.bobs.searchProducts({ query: "sofa", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.bobs.searchProducts({"query": "sofa", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/bobs/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"sofa","limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.bobs.searchProducts({ query: "sofa", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/bobs/<function> - OpenAPI
/v1/sites/bobs/openapi.json