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

A home-search portal in one prompt

"Build me a home search portal for Madrid", running on live data.

You get: A working app in Claude or your code. It uses Location Lookup, Property Sourcing and Area Insights, takes 225 tokens a run (€9.00 at €0.04 a token) and runs per build. For: Software or AI builder, Portal or classifieds.

Status: runs today.

What it does

#StepProductTokens
1locations_searchLocation Lookup0
2property-sourcing_searchProperty Sourcing50
3property-sourcing_next_pageProperty Sourcing50
4property-sourcing_get_property × 10Property Sourcing100
5area-insights_get_time_series_dataArea Insights25

One run: 225 tokens, €9.00. Each call costs the same over MCP and REST, so the run always costs what the table says. How many tokens your volume needs, and plans and credits.

Where it runs

Every country the products it uses cover. The plan names a country that one of them does not.

Run in Claude

This playbook calls 3 Casafari MCP servers. Add each to Claude, ChatGPT or any MCP client, and sign in the first time you use them (a Free account, no card, is created then; console).

  • Location Lookup: https://platform.casafari.com/mcp/locations
  • Area Insights: https://platform.casafari.com/mcp/area-insights
  • Property Sourcing: https://platform.casafari.com/mcp/property-sourcing

In Claude Code:

bash
claude mcp add --transport http casafari-locations https://platform.casafari.com/mcp/locations
claude mcp add --transport http casafari-area-insights https://platform.casafari.com/mcp/area-insights
claude mcp add --transport http casafari-property-sourcing https://platform.casafari.com/mcp/property-sourcing

Then ask:

text
Run the a home-search portal in one prompt playbook for Spain: call locations_search, then property-sourcing_search, then property-sourcing_next_page, then property-sourcing_get_property, then area-insights_get_time_series_data, in that order, and tell me what each step cost in tokens.

Get the API calls

The same steps as REST calls, in order. Create a platform API key in the console and export it as CASAFARI_API_KEY; each call takes the parameters its operation documents in the REST reference.

bash
# 1. Location Lookup, 0 tokens a call
curl -X GET https://platform.casafari.com/v1/locations/search \
  -H "Authorization: Bearer $CASAFARI_API_KEY"

# 2. Property Sourcing, 50 tokens a call
curl -X POST https://platform.casafari.com/v1/property-sourcing/searches \
  -H "Authorization: Bearer $CASAFARI_API_KEY"

# 3. Property Sourcing, 50 tokens a call
curl -X GET https://platform.casafari.com/v1/property-sourcing/searches/{cursor} \
  -H "Authorization: Bearer $CASAFARI_API_KEY"

# 4. Property Sourcing (10 times), 10 tokens a call
curl -X GET https://platform.casafari.com/v1/property-sourcing/properties/{property_id} \
  -H "Authorization: Bearer $CASAFARI_API_KEY"

# 5. Area Insights, 25 tokens a call
curl -X POST https://platform.casafari.com/v1/area-insights/time-series \
  -H "Authorization: Bearer $CASAFARI_API_KEY"

Other playbooks

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