Zoopla MCP server for AI agents
Let Claude, ChatGPT or your own agent read Zoopla: 1 typed function through one MCP server. No Zoopla API key needed.
- Site
- zoopla.co.uk
- Functions
- 1
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Zoopla
An MCP server for Zoopla 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/zooplaEvery site
One MCP server for Zoopla 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
searchSearches property listings by location, price range, and bedrooms.Arguments
Name Type Required args{ location: string, bedrooms?: number, minPrice?: number, maxPrice?: number }Yes Returns
ZooplaProperty[]interface ZooplaProperty { id: string; url: string; price: string; bedrooms?: number; location: string; propertyType?: string; // the site's own labels, read the values off a result, never guess one from prose agentName?: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/zoopla/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.zoopla.search({ location: "London" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.zoopla.search({"location": "London"}))curl -X POST https://api.bowmark.ai/v1/sites/zoopla/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"location":"London"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.zoopla.search({ location: "London" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/zoopla/<function> - OpenAPI
/v1/sites/zoopla/openapi.json