• FindHomes logo
    FindHomesWestern Cape
Search
  • Search
  • AI Agent
  • Map
  • Inspiration
Insights
  • For Sale
  • Sold
Saved
  • Collections
  • Alerts

FindHomes

Works with ChatGPT, Claude, Cursor & your own apps

Bring FindHomes into your AI assistant

Connect FindHomes once, then just ask your AI to search, value, and compare South African property. It does the searching, the maths, and the market analysis for you.

See how it works
See what it can do

Included with FindHomes Plus. No API keys, no code — sign in once and ask.

Real conversations. Real insights.

These are based on real interactions — one message in, deep analysis out, in whichever AI tool you use.

FH

Private Sale Valuation

@findhomes 24 Alma Road, Claremont. Asking R12.5M. 3 bed, 4 bath, 500m² erf. North facing, mountain views, borehole. Is it fair value?
I’ve pulled 14 comparable sales in Upper Claremont from the last 12 months. The median R/m² for similar properties is R24,800.
At 400m² floor area, the benchmark value is ~R9.9M. However, north-facing aspect (+5%), mountain views (+8%), and borehole (+3%) push fair value to ~R11.5M. The asking price of R12.5M carries an 8% premium. I’d recommend offering R11.2–R11.8M.
FH

Dual-Commute Search

@findhomes Properties within 15 min drive from Cape Town City AND 15 min from Century City. Best value for money.
Generating two isochrone polygons for morning peak traffic... Computing the overlap zone. Found 23 properties in the intersection.
Top 3 by value (R/m²): 1. 2-bed in Brooklyn: R1.65M (R12,400/m²) 2. 3-bed in Rugby: R2.1M (R13,800/m²) 3. 2-bed in Maitland: R1.45M (R11,200/m²) Sending you a map with both commute zones and property pins now.
FH

Branded Market Report

@findhomes Compare 3-bed homes in Durbanville vs Brackenfell vs Kraaifontein. Go deep. Synthesize into a PDF with my company's branding.
Screening all three suburbs in parallel... Pulling 50 listings and historical sales for each. Generating your report now.
Done! Your 12-page PDF with your company's branding is ready: includes cover page, market comparison tables, top 5 picks per suburb with links, price growth charts, and investment outlook. Sending it now.

One prompt. Nine superpowers.

Your assistant chains multiple data sources and tools together in a single response: from location lookup to rendered map to branded report.

Property Valuation

"Is R12.5M fair for 33 Alma Road?" Compares against recent sales, factors in views, condition, solar, parking, and more.

Natural Language & Image Search

Search like you talk, or point your assistant at a photo of a property you love — it understands both.

Commute-Based Search

"15 min drive from Sea Point High during morning traffic". Searches within drive-time zones, even dual-commute overlaps.

Market Analysis

Historical sales data, price growth trends, days on market, sale rates, and months of supply for any suburb going back years.

Investment Analysis

Gross yield, cap rate, rental benchmarks, and negotiation strategies. Know if an investment property stacks up before you commit.

Suburb Comparison

"Durbanville vs Brackenfell vs Kraaifontein": side-by-side median prices, R/m², liquidity, and growth potential.

Development Evaluation

Scrapes a development's marketing page, extracts unit prices, and benchmarks against resale market data. Finds the best-value units.

PDF & CSV Reports

Professional reports with your company's branding. Cover pages, market stats, and listing tables delivered straight into your chat.

Market Intelligence

"Is now a good time to sell?" Combines FindHomes data with live web research on rates, trends, and new developments.

How it works

Three steps, about a minute. You never leave the AI tool you already use.

  1. 1

    Get FindHomes Plus

    The AI integration is included with FindHomes Plus — nothing extra to buy.

  2. 2

    Connect your AI tool once

    Sign in with your FindHomes account when your assistant asks. No API keys to copy, no code to write.

  3. 3

    Just ask

    Ask for a search, a valuation, or a suburb comparison in plain language. Your assistant does the rest.

What's the technology behind it?

FindHomes connects to your assistant using MCP (the Model Context Protocol) — an open standard, supported by ChatGPT, Claude, and Cursor, that lets an AI assistant securely use external tools on your behalf. You don't need to understand any of it to use FindHomes: sign in once and ask. Building your own app? The developer details are further down the page.

Connect in under a minute

Pick the AI tool you use and we'll show only the steps for it. Sign in once, then ask about South African property.

For developers

Building your own app or agent? See the full tool reference and rate limits.

Nine tools your assistant can chain together

Name a suburb or describe a commute, then search listings, historical sales, rental yield or a suburb comparison — all in one conversation. Commute zones are resolved on the server, so the model never handles polygons.

Listings, sales and market data

The tools you will use most. Each accepts suburb names or a commute directly, so a single call usually does the job.

Search Properties
search_properties

Search residential for-sale listings in South Africa. Scope by suburb names (locations), location ids, a commute zone, the overlap of two or three commutes, or nothing at all for a nationwide search. Filter by price, bedrooms, bathrooms, flatlets, parking, property type, status, agency, pet-friendliness and a semantic visual_search_description; sort by price, R/m² or listing date. Every result carries a findhomes.co.za URL.

Try asking

“Find pet-friendly 3-bed apartments in Sea Point under R5M with mountain views.”

Search Property Sales
search_property_sales

Historical sale transactions from deeds data, with optional statistics (average, median, min, max, std-dev) and market activity (days on market, absorption, price reductions). Needs a location scope: suburb names, location ids, a commute zone or a polygon. Filter by sale date, price, land or floor size and property type.

Try asking

“Compare median sale prices for 3-bed houses in Durbanville vs Brackenfell over the last 24 months.”

Property Details
property_details

Full details for up to 20 listings by FindHomes property id: rooms, sizes, features, agent and agency contact details, the listing description and the canonical URL.

Try asking

“Give me the agent contact details and full description for the first two results.”

Rental Comparables & Yield
rental_comparables

Comparable rental listings and a gross-yield estimate for a for-sale property. Pair it with property_details and search_property_sales for valuation and investment questions.

Try asking

“What rental yield could I expect on this Observatory flat at R1.8M?”

Screen Suburbs
screen_locations

Compare up to 10 suburbs side by side: median sale price, R/m² land, days on market, percentage under offer, percentage expired, months of supply and sales count over a window (default: the last 24 months). Use it before deep-diving into one suburb.

Try asking

“Screen Wynberg, Plumstead, Claremont and Kenilworth for a first-time buyer.”

Locations and commute zones

Optional previews and disambiguation helpers. The search tools resolve names and build commute zones on the server, so these are for checking a zone or picking between two Kensingtons.

Resolve Location Names
location_resolve

Usually unnecessary: the search tools accept suburb, area and region names directly. Call it to inspect candidates, or after a result with status needs_disambiguation, to see id, name, parent, type, live listing count and similarity per input.

Try asking

“Which Kensington do you mean — Cape Town or Johannesburg?”

Preview a Commute Zone
location_isochrone

Preview a travel-time or distance isochrone around a destination: geocode result, area in km², bounding box and vertex count. It returns no polygon — the model passes the same commute fields to the search tools and the server resolves the zone. arrive_by (driving only) defaults to 09:00.

Try asking

“How big is a 25-minute morning-drive zone around UCT, arriving by 09:00?”

Overlap of Commute Zones
isochrone_intersect

Preview the overlap of two or three commute zones — for example both partners' workplaces — ranked by area, or a NO_OVERLAP status with suggestions. Then the same commutes array goes to search_properties or search_property_sales.

Try asking

“Where can we both live within 30 minutes of Century City and Claremont?”

Client widget

Only used by clients that render MCP App widgets, such as ChatGPT.

ChatGPT Widget
render_property_results

If your client renders MCP App widgets (ChatGPT), this displays search_properties results as property cards. Other clients present the results with their URLs directly.

Try asking

“Show those results as cards.”

Generous limits, predictable behaviour

We rate-limit per signed-in user, not per client, so the cap is yours to use across ChatGPT, Claude, and any other MCP client at the same time.

Per-minute cap

60 tool calls / minute

Plenty for human-paced conversation. The cap is on tools/call only — control-plane methods like tools/list and initialize are free.

Per-day cap

1,000 tool calls / day

The day window resets at midnight UTC. A power user typically runs 50–100 tool calls per day; the cap is here to catch runaway loops, not throttle real work.

Heads-up email at 80%

When you cross 80% of the daily cap, we send one email so you can decide whether to slow down or get in touch about a higher limit. You won't get spammed — exactly one warning per day, even if you keep tool-calling after.

What happens at the cap

The tool call returns HTTP 429 with a Retry-After header telling the client exactly how many seconds to wait. ChatGPT, Claude, and Cursor handle this transparently — you'll see a short pause, then the call resumes.

Need a higher cap for an internal tool, an evaluation harness, or a partner integration? Email founders@findhomes.co.za and tell us about your use case.

Privacy and permissions, in plain English

We only see your tool calls — we don't see anything else, and you can revoke us at any time.

Scopes the connector requests

  • openid
    Confirms you are who you say you are.
  • email
    Lets the client display your email address.
  • profile
    Basic profile metadata used for support and rate limiting.

These are the only OAuth scopes we accept today. We do not use scopes to gate destructive actions; sensitive operations (like saving searches) are gated by your FindHomes account permissions on the server side.

What FindHomes sees

  • Tool calls (which tool, what arguments) — capped at 4 KB per call
  • A SHA-256 hash of your IP address (never the IP itself)
  • Your authenticated user ID and email (for support and rate limits)

What FindHomes never sees

  • The rest of the conversation with ChatGPT, Claude, or Cursor
  • Your prompts that did not trigger a FindHomes tool call
  • Any data the model retrieved from other connectors

More on data handling

Tool-call audit rows are stored on FindHomes infrastructure for support, abuse prevention, and rate limiting. We never sell or share this data with third parties. The full policy is in our privacy policy.

Frequently Asked Questions

Included with FindHomes Plus

Bring property search into your AI workflow.Set up takes about a minute.

Connect FindHomes to ChatGPT, Claude, or Cursor, sign in with your account, and let your assistant handle the searching, the maths, and the market analysis.

Get FindHomes Plus
See how it works

Cookies on FindHomes

We use optional cookies to find bugs, improve the platform, and measure the effectiveness of our advertising. Privacy policy