Platform
Get started

Casafari is the AI agent-native real estate data intelligence platform. The most complete property index in Europe: a deduplicated, cleaned property graph of residential and commercial property, for sale and for rent, in 16 countries.The most complete property index in Europe: a deduplicated, cleaned property graph.

How the graph is built
Markdown Open in Claude Open in ChatGPT

Claro AI · MCP tool

search_premises

Search commercial premises

Separate server67 parameters

Claro AI is a separate MCP server provided by Casafari, not part of https://mcp.casafari.com/. Its address on the platform is https://platform.casafari.com/mcp/claro: Streamable HTTP, a platform API key or the platform's OAuth, metered in platform units. How to connect.

Over REST: POST /v1/search (equivalent). MCP and REST compared.

What does Search commercial premises do?

Find shops, restaurant premises, offices, warehouses and other commercial premises for rent or sale anywhere in Spain. Describe the site in plain words in any language (brief), send criteria as data, or both (criteria override the brief). Returns exact counts (matching, all criteria stated, some not stated), the criteria as understood, and the best results: each with its data, what was met and what its text does not state, the sentence that matched, its coordinates (exact, or snapped to the centre of a ~500 m cell and marked approximate when the agency hides the address; none when it has no pin), a fit verdict read from its text, location figures when your account has location access (footfall, residents, nearby places, and in location the footfall split by weekday/weekend, time of day and where the activity comes from live, plus residents by age, households by income and spending power, each null when not stated or unknown, never 0 for unknown; location_sources gives each figure's unit, source and vintage, and when it was computed), and the agency's own listing link. Our fit verdict is one input: every raw figure is there for your own scoring. Up to 200 results a page (50 with a publishable key). next_cursor gets the next page: send it as cursor (alone, with limit if you like); the order is fixed when the search runs and stays the same for its 24 hours, so pages never repeat or skip a premises. page gives offset, limit and the total ranked. The read-through (check) runs only for pages of up to 50. Keep search_id to refine. Keywords only, no model: send just criteria.keywords and/or exclude_keywords (plus any data criteria) with no brief and check: false, e.g. {"criteria": {"operation": "rent", "cities": ["madrid"], "keywords": [["salida de humos", "sortida de fums"], ["esquina", "chaflán"]], "exclude_keywords": ["se traspasa"]}, "check": false}; each keyword group met carries the sentence that matched (evidence) and the phrase it holds (matched).

Which parameters does search_premises take?

briefstring
The site brief in plain words, e.g. "burger restaurant, corner unit 120-250 m², smoke outlet, busy street, Madrid, rent under 8,000 a month".
criteriaobject
Criteria as data. Hard criteria (operation, cities, types, price, area) exclude properties outside them; the rest exclude only properties that state the opposite, and each result says which were met and which the property does not state.
53 properties
operationstring
rent sale either
citiesstring[]
Spanish towns or cities by name or slug ("valencia", "Palma"). Leave out for all of Spain.
provincesstring[]
Provinces; a property must be in one of them.
52 allowed valuesa-coruna alava albacete alicante almeria asturias avila badajoz barcelona burgos caceres cadiz cantabria castellon ceuta ciudad-real cordoba cuenca girona granada guadalajara guipuzcoa huelva huesca islas-baleares jaen la-rioja las-palmas leon lleida lugo madrid malaga melilla murcia navarra ourense palencia pontevedra salamanca santa-cruz-de-tenerife segovia sevilla soria tarragona teruel toledo valencia valladolid vizcaya zamora zaragoza
districtsstring[]
Named districts or neighbourhoods in the cities (Centro, Malasaña, Chamberí, Eixample, Gràcia, Poblenou...). A property outside them is out; one that does not state its district stays, marked not stated.
typesstring[]
hotel retail warehouse industrial office other_commercial
area_minnumber
area_maxnumber
price_minnumber
EUR: a month for rent, the total for a sale; applies to each operation without its own rent_/sale_ limit.
price_maxnumber
rent_price_minnumber
EUR a month; compared only with rents.
rent_price_maxnumber
EUR a month; compared only with rents. With sale_price_max, operation "either" keeps a property whose rent or sale price fits its own limit.
sale_price_minnumber
EUR total; compared only with sale prices.
sale_price_maxnumber
price_m2_minnumber
EUR per m² of the property's area (a month for rent); a property with no stated area is "not stated".
price_m2_maxnumber
rent_price_m2_minnumber
rent_price_m2_maxnumber
sale_price_m2_minnumber
sale_price_m2_maxnumber
street_levelboolean
frontage_min_mnumber
Facade length (fachada) in metres.
frontage_max_mnumber
floors_minnumber
Number of floors (plantas) the premises has.
floors_maxnumber
ceiling_min_mnumber
smoke_extractionboolean
cornerboolean
shop_windowboolean
open_planboolean
step_freeboolean
loading_accessboolean
licencestring
food_service retail office gym none
licence_activitiesstring[]
Activities its licence sentence must name, in Spanish or Catalan: cafetería, panadería, restaurante...
transfer_price_minnumber
Transfer fee (traspaso) in EUR; met when its stated range overlaps.
transfer_price_maxnumber
business_transferboolean
true: only business transfers (traspasos); false: none.
business_typesstring[]
Uses its text says it suits, in English: restaurant, cafe, gym...
keywordsstring[][]
Groups of phrases; a property meets a group when its text holds any phrase. Write phrases as Spanish agencies do.
exclude_keywordsstring[]
Leave out properties whose text holds any of these.
footfall_minnumber
Minimum footfall index within a 5-minute walk (an index of pedestrian activity that compares places; not a head count). Needs location data access.
pop_walk10_minnumber
Residents within a 10-minute walk. Needs location data access.
pop_drive10_minnumber
Residents within a 10-minute drive. Needs location data access.
transit_minnumber
Stations and stops within a 5-minute walk. Needs location data access.
competitors_maxobject[]
At most this many places of a kind within a 5-minute walk (gyms: 10). Needs location data access.
2 properties
kindstringrequired
restaurants fast_food cafes shops supermarkets gyms
maxnumberrequired
own_stores_away_mnumber
No store from your own list (upload it with PUT /v1/stores) within this many metres of the premises, straight-line, 1-1,000. Needs an exact pin.
competitors_near_maxobject[]
At most max businesses of a segment (or of the named chains) within within_m straight-line metres (1-1,000), from Overture Maps places. A property with an approximate pin gets no verdict.
4 properties
segmentstringrequired
gym burger fast_food coffee bakery pharmacy supermarket fashion pizza
within_mnumberrequired
maxnumberrequired
chainsstring[]
Only these brands count (rivals or your own), e.g. Burger King, Basic-Fit. Matched on Overture brand and name.
spending_per_resident_minnumber
Spending power a resident a year (EUR) within a 10-minute walk. Needs location data access.
high_income_share_minnumber
% of households within a 10-minute walk with net income above 40,162 EUR a year. Needs location data access.
age_shares_minobject[]
Minimum % of residents within a 10-minute walk in an age band. Needs location data access.
2 properties
bandstringrequired
0_14 15_29 30_44 45_59 60p
min_pctnumberrequired
meaningstring
A wish no field holds, in any language; ranks results, never filters.
sortstring
supply_gap ranks where residents per similar place is highest (residents within a 10-minute walk / (places within gap_radius_m, 600 m by default, + 1)); needs gap_segment or one competitors_near_max segment. Needs location data access; unscored properties go last.
best price_asc price_desc area_desc footfall_desc supply_gap
gap_segmentstring
The business kind the supply_gap sort counts.
gym burger fast_food coffee bakery pharmacy supermarket fashion pizza
gap_radius_minteger
Radius in metres in which the supply_gap sort counts similar places: 600 (default) or 300 (about a 5-minute walk). Only with sort supply_gap.
300 600
limitinteger
Results a page, up to 200; above 50 check is off.
1–200default 10
cursorstring
next_cursor from an earlier answer: returns that search's next page, same criteria and order. Send without brief, criteria or change.
checkboolean
Read the top results' text against the brief (adds a few seconds). Off above 50 results a page and on later pages.
default true
insightsboolean
Add insights, charts as data over every match, each with a one-sentence answer, its count, scope, source and date: per criterion how many matches meet it, leave it unsaid or contradict it (and how many would state everything without it); with one price limit, what it reaches among premises of this kind and place before the limit, else what the matches ask per m²; and where the matches are by district or town. Asking prices; each unit counted once.
default false

How do I call search_premises?

Required arguments only, with placeholder values. Your assistant fills them in from the parameters above.

JSON-RPC
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_premises",
    "arguments": {
      "brief": "…"
    }
  }
}
Esc

Tip: add .md to any URL to read it as Markdown.