Castlery Furniture MCP server for AI agents
Let Claude, ChatGPT or your own agent read Castlery Furniture: 2 typed functions through one MCP server. No Castlery Furniture API key needed.
- Site
- castlery.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Castlery Furniture
An MCP server for Castlery 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/castleryEvery site
One MCP server for Castlery 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 2
getProductReads one Castlery product page.Arguments
Name Type Required urlstringYes Returns
CastleryProductinterface CastleryProduct { sku: string | null; name: string; description: string | null; category: string | null; material: string | null; price: number | null; // USD, the live offer currency: string | null; availability: string | null; // "InStock", "OutOfStock", … rating: number | null; reviewCount: number | null; dimensions: string | null; // e.g. 'W72.8" x D35.4" x H29.5"' specs: Record<string, string>; images: string[]; variantCount: number; url: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/castlery/getProductCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.castlery.getProduct("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.castlery.getProduct("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/castlery/getProduct \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"<url>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.castlery.getProduct("<url>");searchSearches or browses Castlery's furniture and home-goods catalog by keyword, returning matching products with name, price, sale price (if on sale)…Arguments
Name Type Required querystringE.g. "sofa", "dining table", "dawson".Yes Returns
CastlerySearchResult[]interface CastlerySearchResult { sku: string | null; name: string; url: string; // pass to getProduct tagline: string | null; // e.g. "Oak Veneer, Curvy Top & Legs" price: number | null; // USD, the live price wasPrice: number | null; // struck price when on sale variantsNote: string | null; // e.g. "2 sizes available" }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/castlery/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.castlery.search({ query: "sofa" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.castlery.search({"query": "sofa"}))curl -X POST https://api.bowmark.ai/v1/sites/castlery/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"sofa"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.castlery.search({ query: "sofa" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/castlery/<function> - OpenAPI
/v1/sites/castlery/openapi.json