MCP App Store
by KeenEthics
Húsasjá icon

Húsasjá MCP Server for ChatGPT

By Neko Management ehf.

Overview

Húsasjá brings Iceland's housing market into ChatGPT. Ask about homes for sale, what nearby homes have sold for, a specific building or apartment, and what Húsasjá's figures mean. What you can do: - Search homes currently for sale anywhere in Iceland by area, price, size, rooms and features such as a balcony, garage or elevator. Results appear as a row of sale cards with photos, price and size, each linking to the home on husasja.is. - See what is for sale near a given address, sorted by distance. - Look up recent sales and asking prices on a street or in an area, with price per square metre. - Look up a building: construction year, floors, number of units and its approved blueprints. - Find a specific apartment by address and get Húsasjá's estimated market value for it, the same estimate the Húsasjá app shows. - Compare listings side by side, see a listing's details and price history, and get an estimate of how long a home takes to sell. - Get explanations of Húsasjá's concepts, such as the market value estimate, the price index and time on market. Who it is for: people buying, selling or following homes in Iceland, and anyone who wants to understand prices in a neighbourhood. Limitations: - Covers Iceland only. - Read-only. It does not save, change or send anything. - Market value estimates are statistical models built from comparable sales. They are not appraisals by a licensed real estate agent. - Requires signing in with a Húsasjá account.

How to connect

  1. ChatGPT: Open the Húsasjá listing in the ChatGPT app directory and choose Connect. ChatGPT listing Húsasjá exposes 17 tools here.

Tools

compare_properties

ChatGPT
Compare 2–4 listings side by side: price, size, price per m², rooms and location. Use when the user asks to compare specific properties. Needs listing (market episode) ids from search results.

explain_concept

ChatGPT
Húsasjá's own explanation of one topic from its help pages, in Icelandic: what a figure in Húsasjá means, how it is computed and where its limits are, or how a part of the app works. Use it when the user asks how Húsasjá arrives at a number (verðmat, the price index, sölutími, kaupgeta and the like) or how a feature works, so the explanation matches what Húsasjá shows. One topic per call. Topics: - map: Kortið (Að nota Húsasjá) - filters: Síur (Að nota Húsasjá) - sale-cards: Söluspjöldin (Að nota Húsasjá) - property: Eignasýnin (Að nota Húsasjá) - comparables: Samanburður (Að nota Húsasjá) - buyability: Kaupgeta (Að nota Húsasjá) - saved-searches: Vaktaðar leitir (Að nota Húsasjá) - snjallleit: Snjallleit (Að nota Húsasjá) - dashboard: Verðvísar (Að nota Húsasjá) - sale: Sala, auglýsing og kaupsamningur (Hvað tölurnar merkja) - price-index: Vísitalan (Hvað tölurnar merkja) - nominal-and-real: Nafnverð og raunverð (Hvað tölurnar merkja) - valuation: Verðmat (Hvað tölurnar merkja) - time-on-market: Sölutími (Hvað tölurnar merkja) - asking-vs-sale-price: Munur á ásettu verði og söluverði (Hvað tölurnar merkja) - comparable-sales: Sambærilegar sölur (Hvað tölurnar merkja)

find_building_by_address

ChatGPT
Resolve an address to a building_id (and candidates for disambiguation) — the entry point for the building-scoped tools. Fuzzy-matches street name; narrow with house number, postcode, municipality, or construction-year range. The result's match says how the search resolved. single: one building; use its building_id with the other tools. ambiguous: a street and house number matched several buildings (the same address in two towns, say) and one is meant; name the building you would base the answer on (address, construction year), list the others briefly and ask the user which one they mean; never pick one yourself. several: a street or area search, and every building returned is meant; open the answer by saying it covers N buildings ('Miðað við N byggingar…'). none: nothing matched; ask the user to check the address. When truncated is true, more buildings matched than were returned: raise top_k or narrow with postcode or construction year. When unmatched_place is set, the municipality given names no region, municipality or town, so nothing was searched: try the postcode, or the town name in Icelandic.

find_current_real_estate_listings

ChatGPT
Search current real estate listings for sale in Iceland (íbúðir/hús til sölu) by location, size, price, rooms and amenities. Use for open-ended property search. When unmatched_place is set, the municipality given names no region, municipality or town, so nothing was searched: use lookup_postcodes to find the area's postcodes. In clients that show apps, the results also appear to the user as a scrollable row of sale cards (photos, price, size, address) they can click through to Húsasjá. There, don't enumerate or tabulate the listings in your reply: write a short summary of what matched (how many, the price and size ranges). In clients without apps, your reply is the user's only view of the results: list the listings that answer their question (address, price, size, rooms, and the Húsasjá link where the result gives one) and say how many matched in all (total_count). Listing ids are for follow-up calls (get_listing_detail, compare_properties), never for the user.

find_nearby_listings

ChatGPT
Current listings for sale near a building, sorted by distance — for "what else is for sale nearby". Needs a building_id from find_building_by_address. It finds none when no listing lies within the radius or the building has no location; find_current_real_estate_listings with the building's postcode searches wider. In clients that show apps, the results also appear to the user as a scrollable row of sale cards (photos, price, size, address) they can click through to Húsasjá. There, don't enumerate or tabulate the listings in your reply: write a short summary of what matched (how many, the price and size ranges). In clients without apps, your reply is the user's only view of the results: list the listings that answer their question (address, price, size, rooms, and the Húsasjá link where the result gives one) and say how many matched in all (total_count). Listing ids are for follow-up calls (get_listing_detail, compare_properties), never for the user.

find_unit_by_address

ChatGPT
Resolve a specific unit (apartment or house) to its unit_id (fastanúmer) from an address, narrowed by unit code (íbúðanúmer, e.g. '0201') when the building has several; or list every unit in a building by building_id. The entry point for the unit-scoped tools: market value, sale history and latest listing. The result's match says how the address resolved. single: one unit; use its unit_id with the other tools. ambiguous: several units match and one is meant. Clients that show apps show the user these units to pick from, and their pick arrives as their next message: treat it as the answer and resolve the unit it names, without listing the units again. In clients without apps, name the unit you would base the answer on (address, size, rooms), list the other candidates briefly and ask the user which one they mean; never pick one yourself. several: every unit in the building given by building_id, and all of them are meant; open the answer by saying it covers N units in the building ('Miðað við N íbúðir í þessari byggingu…'). none: nothing matched; ask the user to check the address. When truncated is true, more units matched than were returned: narrow the search with postcode, house_number or unit_code. When unit_code_found is false, no unit at the address has the unit code given: tell the user so, then treat the address's units in units as ambiguous.

get_building_info

ChatGPT
Building-level facts: construction year, floors, number of units, and blueprints (teikningar). Use when the user asks about a building as a whole. Needs a building_id from find_building_by_address or find_unit_by_address.

get_expected_days_to_sell

ChatGPT
Liquidity estimate — how long a property is expected to take to sell. Pass unit_id for a unit-specific estimate (most precise), or building_id / postcode for area-level statistics.

get_listing_detail

ChatGPT
Full detail for one listing: price, size, rooms, amenities, the building, and maintenance. Use to go deeper into one property from a search. Needs a listing (market episode) id from a search result or resolve_latest_listing_for_unit.

get_nearby_amenities

ChatGPT
Amenities near a building: kindergartens (leikskóli), schools, grocery stores and bus stops, with distances, optionally one category. Use for 'what's nearby' questions. Needs a building_id from find_building_by_address.

get_sale_cards

ChatGPT
Sale rows for the sale-card view, by sale ref (sale:123); a bare number is a market-episode id. Called by the view, not the model.

get_sales_and_listings_history

ChatGPT
Micro-comparables: recent sales and active listings around a location, with size/room filters. Prefer a building_id from find_building_by_address; otherwise pass a street_name (optionally a postcode to disambiguate). Widen or narrow with scope.

get_unit_market_value

ChatGPT
Húsasjá's estimated market value for a unit, the same estimate the app shows: the value, price per m², comparable properties' price per m², and expected days on market. Computed from comparable sales; it is a statistical estimate, not an appraisal by a licensed agent. Use for a unit that isn't listed, or to set an asking price beside the estimate. Needs a unit_id from find_unit_by_address. Some units have no estimate (the valuation model can't value them, and the app shows none either); then say so.

get_unit_picker

ChatGPT
The building whose units the unit-picker view lists. Called by the view, not the model.

get_unit_sale_history

ChatGPT
A unit's recorded sales: past prices and dates. Use for 'has this been sold before' and price-history questions. Needs a unit_id from find_unit_by_address.

lookup_postcodes

ChatGPT
Resolve a municipality or neighbourhood name to postcodes — a helper for the area-scoped tools when you only have a place name. Pass the postcodes to find_current_real_estate_listings (its postcodes parameter) or another location-based tool; for a region, municipality or town, find_current_real_estate_listings also takes the name directly as municipality, which covers the same postcodes. Each of places is one place the name resolved to. exact false means the name matched by alias, part of the name or approximately, so the place may not be the one meant. A district's or matsvæði's postcodes carry share, how much of the place lies inside each: postcodes don't follow district lines, so a postcode can reach into a neighbouring district. A name can match matsvæði in more than one municipality, and a district split into matsvæði under other names (Reykjavík's Vesturbær, for one) is only partly covered: check the places before using every postcode. Empty places means nothing matched: try the Icelandic name of the town or municipality (e.g. 'Kópavogur', 'Akureyri'), a region such as 'Höfuðborgarsvæðið', or the district's own name.

resolve_latest_listing_for_unit

ChatGPT
A unit's current or most recent listing (market episode) id, with summary fields — the bridge from a unit the user named to get_listing_detail. If the unit has never been listed (result is null), use get_unit_market_value for an estimate instead. Needs a unit_id from find_unit_by_address.

Capabilities

Interactive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/h-sasj"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/h-sasj)