MCP server examples: what Casafari MCP can do

Real questions people ask a real estate MCP server, the tools an assistant calls to answer them, and what comes back. Ask the question in plain words in any MCP client; the assistant picks the tools.

#Area trend: how have prices moved?

"How has the asking price per m² of flats in Valencia moved over the last three years?"

1. ma_get_location_typeahead turns "Valencia" into a location id.
2. ma_get_time_series_data returns the average asking price per m² per month (data_point: avg_price_psqm).
3. ma_get_time_series_operations computes the change and growth rate over the period (delta_pct, cagr).

{
  "name": "ma_get_time_series_data",
  "arguments": {
    "request_data": {
      "alias": "Valencia flats",
      "type_group": "apartment",
      "business_type": "sale",
      "custom_location_boundary": { "location_ids": [12345] },
      "data_point": "avg_price_psqm",
      "date_interval": "month",
      "date_range": { "min": "2023-10-01" }
    }
  }
}

The location id here is a placeholder: the first call supplies the real one.

#Price bands and time on market

"What are the asking prices of 2-bedroom flats in Lisbon, and how long do they stay on the market?"

• ma_get_price_distribution: how many properties on the market fall in each asking-price band.
• ma_get_bedrooms_distribution: count, average price and price per m² by bedrooms.
• ma_get_time_on_market_distribution: average days on market per price band.

#Compare districts

"Which districts of Madrid have the highest price per m²?"

ma_get_heatmap returns one value per district (child location) of a city or region, ready for a map.

#Value a home from comparables

"What is a 3-bedroom flat near Avenida da Liberdade, Lisbon worth? Use comparables within 1 km."

comps_get-comparables finds comparable properties around a point, an address or a Spanish cadastral reference, and returns them with statistics and an estimated price range: fair market value, quick-sale price and premium price.

#Find agencies worth partnering with (AgentGraph AI)

"Which independent agencies in München are growing faster than the market?"

1. agentgraph_find_location resolves the area.
2. agentgraph_screen_agencies ranks the agencies against partner profiles, with their figures and the signals they meet.
3. agentgraph_partner_brief writes a one-page brief on one of them.

#Reports and applications

• Reports. Ask the assistant to combine the calls above into a market report for an area: trend, price bands, time on market and district comparison, with the figures the tools returned and the period they cover.
• Applications. For a fixed workflow in your own software, call the same data from code through the REST API at https://api.casafari.com; MCP vs REST API shows which data each offers.