CB2 MCP server for AI agents
Let Claude, ChatGPT or your own agent read CB2: 1 typed function through one MCP server. No CB2 API key needed.
- Site
- cb2.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just CB2
An MCP server for CB2 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/cb2Every site
One MCP server for CB2 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 CB2's furniture and decor catalog the way its own search box does ("sofas") and returns products with current and regular price…Arguments
Name Type Required querystringWhat CB2's own search box takes, e.g. "sofas", "velvet sectional".Yes sort"relevance" | "price_ascending" | "price_descending" | "top_rated" | "best_selling" | "newest"No pagenumberFrom 1.No limitnumber1-100, default 24.No Returns
Cb2Searchinterface Cb2Product { sku: string; name: string; // e.g. 'Berkeley 106" Jade Performance Velvet Sofa' url: string; // the product page on www.cb2.com price: number | null; // current price of THIS size/colour, USD regularPrice: number | null; // its regular (non-sale) price, USD onSale: boolean; // a sale or clearance markdown priceLabel: string | null; // the store's own word: "Sale", "Clearance" familyName: string | null; // the product family, e.g. 'Berkeley Jade Performance Velvet Sofa (78"-106")' familyPriceMin: number | null; // lowest price across the family's sizes, USD familyPriceMax: number | null; types: string[]; // e.g. ["Sofas"] rating: number | null; // 0-5 reviewCount: number | null; availability: string[]; // e.g. ["InStock"], ["InStock", "Backorder"] isNew: boolean; finalSale: boolean; widthInches: number | null; description: string; imageUrl: string | null; } interface Cb2Search { products: Cb2Product[]; 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/cb2/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.cb2.searchProducts({ query: "sofas", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.cb2.searchProducts({"query": "sofas", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/cb2/searchProducts \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"sofas","limit":5}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.cb2.searchProducts({ query: "sofas", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/cb2/<function> - OpenAPI
/v1/sites/cb2/openapi.json