search_premises

Call it as search_premises on the Claro AI MCP server, https://platform.casafari.com/mcp/claro (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 or Germany (one country per search; Spain unless Germany is asked). 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 (fit: good, partial or poor, a reason, the quote it rests on; data_conflict when its text names another district, city or property type than its own data, with the text's words and a note to check the agency's ad: the data decides the verdict, an exact pin over any place the text names), 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 (agency.name) with its own listing page as agency.listing_url, null when the agency has no page of its own (always the agency's own page, never a property portal's). 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. stated_only: true pages through only the matches that state every criterion (those with a point not stated or not met are left out; counts still gives both totals, page.total the set being paged); send it with the first search, or with search_id to page a stored search's stated matches without searching again, and its next_cursor keeps it. search_id with offset (and no brief, criteria or change) returns that search's page from that place. pins_only: true with search_id (or a cursor) returns just each match's pin, pins (id, lat, lon, precision, plus type, district, rent and sale price, size and the day it was first listed, listed_since, each null when not stated), up to 2000 a page, for a map. 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?

#How do I call search_premises?

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

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

#Related pages

• Refine a search (refine_search)
• Get one premises (get_premises)
• Compare premises (compare_premises)
• What premises ask in a place (market_snapshot)
• Claro AI: all its MCP tools and REST operations
• Connect Claro to an MCP client