Score every premises with your own agent
For AI Agent Builder. Use search_premises to identify targets and then iterate through pages using next_cursor to retrieve every match and its location figure sources.
MCP tool: search_premises (REST: POST /v1/claro/search)
How to score premises programmatically
To ensure your agent evaluates every candidate, you must iterate through search results using pagination. Perform an initial search, and if more results exist, send the next_cursor as cursor in your next call to POST /v1/claro/search.
POST https://platform.casafari.com/v1/claro/search
Authorization: Bearer $CASAFARI_API_KEY
{
"brief": "commercial retail in Madrid",
"limit": 50
}You get a list of premises, each with its own data and location figures. You use the opaque pm_ ID to retrieve full details or perform comparisons. Limits include a maximum of 200 results per page (50 if check is enabled).