CasafariMCP
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
22 tools behind one endpoint

Property data intelligence,
built for AI agents.

Casafari is the AI agent-native real estate data intelligence platform. Deduplicated, cleaned property graph. Europe's most complete property index.

  • Residential and commercial
  • For sale and for rent
  • Every price change
  • Full property history

One question, the whole market

Your assistant turns a plain question into the right tool calls. Casafari MCP signs you in, checks your rights and answers from the property graph and market series, in seconds.

Question travels over MCPAnswer comes back with the evidence

Illustration with sample figures. Real answers quote what the tools return, with the period and filters used.

The property graph

Much more than listings

Listings are where Casafari starts, not what it delivers. Every listing from agency websites and portals in 16 countries is structured, cleaned and deduplicated, and all the listings of a property are merged into one record that keeps its whole history: every price change, every status change, every listing and delisting. That is the most complete property index in Europe, for every asset class, for sale and for rent.

Illustration with sample figures.

  1. 1Collect

    Listings from agency websites and portals in 16 countries, as they appear and as they change.

  2. 2Structure

    Every listing into one schema: type, operation, price, area, rooms, features, condition, energy rating and location.

  3. 3Clean

    Values normalised, places resolved to the location tree and to coordinates, outliers flagged.

  4. 4Deduplicate

    The same property, advertised by several agencies and portals, recognised as one.

  5. 5Merge into the graph

    One record per property, linking its listings, agencies, agents, location and history.

16 countries

One schema and one location tree in every market.

Residential and commercial

Apartments to villas, offices, retail, hotels, warehouses, plots, garages, buildings and new developments.

Sale and rent

Both operations on the same property record.

Full history

Every price change, status change, appearance and delisting, with dates.

How the property graph is built, and where it shows in the API

What's inside

Products, each documented from its own definitions: the MCP tools and the REST operations that serve it, every parameter, the response and a call you can copy. See what exists over MCP, over REST or both.

Ask in plain words

Your assistant picks the tools, resolves places to locations, calls them and explains the answer.

  • Comparables & ValuationWhat is a 3-bedroom flat near Avenida da Liberdade, Lisbon worth? Use comparables within 1 km.
  • Area InsightsHow has the asking price per m² of flats in Valencia moved over the last three years?
  • AgentGraph AIWhich independent agencies in München are growing faster than the market?

Connect in one step

One URL for every Casafari group. The first time, your client opens Casafari's sign-in; the assistant then sees exactly the tools your subscription covers.

All clients and options

Claude
Settings → Connectors → Add custom connector
Name: Casafari
URL:  https://mcp.casafari.com/

Agent-ready, end to end

The docs are written for agents as much as for people. Every page is also Markdown, and the standard discovery documents point agents to the server.

Any page as Markdown
curl -H "Accept: text/markdown" \
  https://platform.casafari.com/docs/area-insights/get_time_series_data

Questions and answers

What is Casafari MCP?

Casafari MCP is a single remote MCP server, https://mcp.casafari.com/, that gives an AI assistant or agent access to Casafari's real estate data: 22 data tools across 3 products.

Casafari describes itself as the AI agent-native real estate data intelligence platform. The server uses Streamable HTTP and signs you in with OAuth 2.1 through your Casafari account. It acts as a gateway: it signs the user in, checks the account's rights on every call, and forwards each tool to the service that owns it. The products available over MCP are Comparables & Valuation, Area Insights and AgentGraph AI. The gateway also adds its own list_servers, which shows which products your account can use. The same data is also available through a REST API.

See: Casafari MCP, Connect your assistant, All tools, The property graph.

Which countries does Casafari cover?

Casafari's API permissions list exactly 16 markets, and the documentation names no others. The market a given tool serves is only what that tool's own description says.

  • Andorra (AD)
  • United Arab Emirates (AE)
  • Austria (AT)
  • Belgium (BE)
  • Switzerland (CH)
  • Germany (DE)
  • Spain (ES)
  • France (FR)
  • Greece (GR)
  • Italy (IT)
  • Luxembourg (LU)
  • Monaco (MC)
  • Poland (PL)
  • Portugal (PT)
  • San Marino (SM)
  • United States (US)

A few tools name a market in their own description. See per-tool coverage. The documentation publishes no other country count.

See: Casafari MCP, AgentGraph AI, Comparables & Valuation, POST /api/v1/references/locations/typeahead.

For anything not covered here, contact Casafari: https://www.casafari.com/

Which products does Casafari MCP offer, and how many tools are there?

Casafari MCP offers 22 data tools across 3 products behind the gateway, plus list_servers. Three more products are available over the REST API only, 39 operations in all.

Over MCP:

Over REST only:

Comparables & Valuation and Area Insights also have REST operations (4 and 6, respectively).

See MCP and REST compared, and find every tool's schema at /tools.json.

Which AI assistants and MCP clients work with Casafari MCP?

Casafari MCP works with any client that supports remote MCP servers over Streamable HTTP with OAuth. The Connect guide has steps for Claude, ChatGPT, Claude Code, Cursor and VS Code.

  • Claude: add a custom connector with the server URL.
  • ChatGPT: create a connector in Developer mode and select OAuth.
  • Claude Code: run claude mcp add --transport http casafari https://mcp.casafari.com/.
  • Cursor and VS Code: add an entry to mcp.json.
  • Any other client or your own agent: point it at https://mcp.casafari.com/. It discovers the sign-in metadata from the 401 response and registers itself using dynamic client registration with PKCE.

In every case, you sign in with your Casafari account, and the assistant acts with that account's permissions.

See: Connect your assistant and Authentication.

How much does Casafari MCP cost?

Casafari doesn't publish prices for Casafari MCP or the REST API. Its MCP page describes "flexible pricing based on your AI application needs" and asks you to contact Casafari.

Access is tied to a Casafari account and the matching subscription. A token carries exactly that account's rights, tools/list shows only the tools it covers, and each product has a quota, though the figure isn't published.

See: How do I get access? and the Casafari MCP page.

For a quote, contact Casafari through the MCP page: https://www.casafari.com/products/property-data-mcp-ai-agents/

All questions

Start with one question

Connect, sign in, and ask what you would ask an analyst.

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