Room & Board MCP server for AI agents
Let Claude, ChatGPT or your own agent read Room & Board: 2 typed functions through one MCP server. No Room & Board API key needed.
- Site
- roomandboard.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Room & Board
An MCP server for Room & Board 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/roomandboardEvery site
One MCP server for Room & Board 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
listCategoriesLists every Room & Board department and category (Living › Sofas and Loveseats, Bedroom › Beds, …) with its page link and how many products it holds.Arguments
None.
Returns
RoomAndBoardCategory[]interface RoomAndBoardCategory { department: string; // slug, e.g. "living" category: string; // slug, e.g. "sofas-and-loveseats" name: string; // e.g. "Sofas and Loveseats" url: string; productCount: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/roomandboard/listCategoriesCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.roomandboard.listCategories();import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.roomandboard.listCategories())curl -X POST https://api.bowmark.ai/v1/sites/roomandboard/listCategories \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.roomandboard.listCategories();searchProductsSearches Room & Board's furniture catalog by product name and category ("leather sofa", "dining table") and returns each matching product's name…Arguments
Name Type Required querystringE.g. "leather sofa", "metro", "dining table".Yes departmentstringNarrow to one department, e.g. "living", "bedroom", "outdoor".No limitnumber1-100, default 24.No Returns
RoomAndBoardSearchinterface RoomAndBoardProduct { slug: string; // e.g. "metro-sofas" name: string; // from the product's own URL, e.g. "Metro Sofas" url: string; // the product page on www.roomandboard.com department: string; // e.g. "Living" categories: string[]; // every category it is filed under, e.g. ["Sofas and Loveseats", "Sectionals"] } interface RoomAndBoardSearch { products: RoomAndBoardProduct[]; total: number; // all matches, before limit }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/roomandboard/searchProductsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.roomandboard.searchProducts({ query: "sofa", limit: 5 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.roomandboard.searchProducts({"query": "sofa", "limit": 5}))curl -X POST https://api.bowmark.ai/v1/sites/roomandboard/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.roomandboard.searchProducts({ query: "sofa", limit: 5 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/roomandboard/<function> - OpenAPI
/v1/sites/roomandboard/openapi.json