Finders Keepers MCP server for AI agents
Let Claude, ChatGPT or your own agent read Finders Keepers: 2 typed functions through one MCP server. No Finders Keepers API key needed.
- Site
- finders.co.uk
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Finders Keepers
An MCP server for Finders Keepers 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/findersEvery site
One MCP server for Finders Keepers 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 finders.co.uk Oxford letting (incl. student and shared houses) by its link or property number: address, monthly rent, deposit, bedrooms…Arguments
Name Type Required listingstringYes Returns
FindersListingtype FindersStatus = "available" | "let_agreed" | "let" | "not_found"; interface FindersListing { propertyNumber: string; url: string; status: FindersStatus; // "not_found" carries only propertyNumber and url statusLabel?: string; address?: string; postcode?: string | null; priceAmount?: number | null; priceFrequency?: "pcm"; priceText?: string | null; bedrooms?: number | null; bathrooms?: number | null; propertyType?: string | null; isStudent?: boolean; branchName?: string | null; summary?: string | null; image?: string | null; depositAmount?: number; councilTaxBand?: string; availableDate?: string; // dd/mm/yyyy as printed furnishing?: string; reference?: string; features?: string[]; description?: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/finders/getListingCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.finders.getListing("<listing>");import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.finders.getListing("<listing>"))curl -X POST https://api.bowmark.ai/v1/sites/finders/getListing \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"listing":"<listing>"}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.finders.getListing("<listing>");searchListingsLists the Oxford properties Finders Keepers (finders.co.uk) has to let, ten per page with a hasMore flag, each with rent, bedrooms, status and a link…Arguments
Name Type Required pagenumberNo Returns
FindersSearchResultinterface FindersListingSummary { propertyNumber: string; url: string; address: string; postcode: string | null; priceAmount: number | null; priceFrequency: "pcm"; priceText: string | null; // the site's own, e.g. "£3,200 pcm" bedrooms: number | null; bathrooms: number | null; propertyType: string | null; // the site's own, e.g. "apartment", "detached house" isStudent: boolean; status: "available" | "let_agreed" | "let"; statusLabel: string; // the site's own word, e.g. "To let", "Let agreed" branchName: string | null; summary: string | null; image: string | null; } interface FindersSearchResult { listings: FindersListingSummary[]; page: number; hasMore: boolean }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/finders/searchListingsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.finders.searchListings({});import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.finders.searchListings({}))curl -X POST https://api.bowmark.ai/v1/sites/finders/searchListings \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.finders.searchListings({});
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/finders/<function> - OpenAPI
/v1/sites/finders/openapi.json