1stDibs MCP server for AI agents
Let Claude, ChatGPT or your own agent read 1stDibs: 2 typed functions through one MCP server. No 1stDibs API key needed.
- Site
- 1stdibs.com
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just 1stDibs
An MCP server for 1stDibs 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/firstdibsEvery site
One MCP server for 1stDibs 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
getListingReads one listing's real price and its concrete completing action (Make an Offer and/or Contact Seller.Arguments
Name Type Required urlstringYes Returns
FirstdibsListinginterface FirstdibsCompletingAction { makeOffer: boolean; contactSeller: boolean; purchase: false; } interface FirstdibsListing { name: string; url: string; description: string; brand: string | null; price: number; priceCurrency: string; completingAction: FirstdibsCompletingAction; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/firstdibs/getListingCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.firstdibs.getListing("<url>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.firstdibs.getListing("<url>"))curl -X POST https://api.bowmark.ai/v1/sites/firstdibs/getListing \ -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.firstdibs.getListing("<url>");searchRuns 1stDibs' search and returns real listings.Arguments
Name Type Required querystringYes Returns
FirstdibsSearchResult[]interface FirstdibsSearchResult { name: string; url: string; price: number; priceCurrency: string; availability: string; // the site's own labels, read the values off a result, never guess one from prose image: string | null; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/firstdibs/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.firstdibs.search("sofa");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.firstdibs.search("sofa"))curl -X POST https://api.bowmark.ai/v1/sites/firstdibs/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"sofa"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.firstdibs.search("sofa");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/firstdibs/<function> - OpenAPI
/v1/sites/firstdibs/openapi.json