Redfin MCP server for AI agents
Let Claude, ChatGPT or your own agent read Redfin: 1 typed function through one MCP server. No Redfin API key needed.
- Site
- redfin.com
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Redfin
An MCP server for Redfin 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/redfinEvery site
One MCP server for Redfin 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
searchLists homes for sale on Redfin in one city, neighborhood or county.Arguments
Name Type Required querystring | { url?: string; regionId?: number; regionType?: number; minPrice?: number; maxPrice?: number; minBeds?: number; propertyType?: string; limit?: number }Yes Returns
RedfinSearchinterface RedfinHome { propertyId: string; listingId: string | null; address: string | null; city: string | null; state: string | null; zip: string | null; price: number | null; beds: number | null; baths: number | null; sqft: number | null; lotSqft: number | null; yearBuilt: number | null; propertyType: string | null; // house, condo, townhouse, multi-family, land, … status: string | null; // MLS status: "Active", "Coming Soon", "Pending" latitude: number | null; longitude: number | null; remarks: string | null; // the listing description url: string; // the home's redfin.com page } interface RedfinSearch { regionId: number; regionType: number; scanned: number; // rows Redfin returned (max 350) before filters total: number; // rows after filters homes: RedfinHome[]; warnings: string[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/redfin/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.redfin.search("<query>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.redfin.search("<query>"))curl -X POST https://api.bowmark.ai/v1/sites/redfin/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"query":"<query>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.redfin.search("<query>");
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/redfin/<function> - OpenAPI
/v1/sites/redfin/openapi.json