GUTHMANN® Berlin Real Estate
RemoteAbout GUTHMANN® Berlin Real Estate
GUTHMANN® Berlin Real Estate gives AI agents access to Berlin property listings, market data, and area information. The service requires no API key or registration and includes granular data from boroughs to neighborhoods.
Key features
- 01Search active listings with filters
- 02Retrieve listing details and exposés
- 03Query Berlin and Germany market indicators
- 04Explore borough and neighborhood data
- 05Access demographic, macro, and zoning data
- 06Search site content and field metadata
Use cases
- 01Filter properties by area, price, and size
- 02Compare market data across Berlin neighborhoods
- 03Look up Berlin areas and demographic information
MCP support
It exposes tools for listing searches, market data, area information, and site search through a stateless Streamable HTTP MCP server. MCP clients can connect to the public endpoint without credentials.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.guthmann.estate/mcpclaude mcp add --transport http estate-guthmann https://mcp.guthmann.estate/mcp{"mcpServers":{"estate-guthmann":{"type":"http","url":"https://mcp.guthmann.estate/mcp"}}}Open in Cursor{"servers":{"estate-guthmann":{"type":"http","url":"https://mcp.guthmann.estate/mcp"}}}Open in VS Code{"mcpServers":{"estate-guthmann":{"type":"http","url":"https://mcp.guthmann.estate/mcp"}}}{"mcpServers":{"estate-guthmann":{"serverUrl":"https://mcp.guthmann.estate/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
37This tool takes no parameters.
Details
From the project README
GUTHMANN® Berlin Real Estate MCP Server
Berlin real estate for AI agents: granular market data and property search.
Free, no API key, no registration — connect and query.
https://mcp.guthmann.estate/mcp
Streamable HTTP, stateless, rate-limited at 60 requests per minute per IP. Listed in the official MCP Registry as estate.guthmann/mcp.
What you can ask
Which neighbourhoods make up the Berlin district of Pankow?
Find the LOR planning area for Kollwitzkiez and show its details.
Show me apartments for sale in Prenzlauer Berg under 500k EUR.
What does GUTHMANN say about Milieuschutz and what it means for buyers?
List all 12 Berlin boroughs with their key facts.
Connect
Claude Code
claude mcp add --transport http guthmann https://mcp.guthmann.estate/mcp
Claude.ai / Claude Desktop — Settings → Connectors → Add custom connector, then paste the server URL above.
Cursor — use the install button above, or add manually:
{
"mcpServers": {
"guthmann": {
"url": "https://mcp.guthmann.estate/mcp"
}
}
}
VS Code — use the install button above, or add to your MCP configuration:
{
"servers": {
"guthmann": {
"type": "http",
"url": "https://mcp.guthmann.estate/mcp"
}
}
}
Any other MCP client with Streamable HTTP support works the same way — point it at the server URL, no credentials needed.
Tools
The full public Market Intelligence scope of guthmann.estate plus the GUTHMANN listings — 37 tools across seven groups, at the same granularity as the website. Berlin's spatial hierarchy: 12 boroughs (Bezirke), 96 districts (Ortsteile), 542 neighborhoods (LOR Planungsräume).
Site search — semantic search over the whole website (insights, market reports, neighborhood portraits, exposés, company pages), one result per page with title, snippet and URL:
| Tool | What it returns |
|---|---|
search | Hybrid semantic search, filterable by locale and section (listings, projects, market-intelligence, pages) |
Property search — the broker's active inventory, every result with its exposé URL:
| Tool | What it returns |
|---|---|
listings | Active listings, filterable by segment, borough/district, price, rooms, area |
listing_details | One listing in detail: prices, costs, energy certificate, texts, images, contact |
Berlin market data — granular transaction and offer aggregates:
| Tool | What it returns |
|---|---|
market_berlin_apartments | Flats: transaction prices, offer prices, offer rents, counts, deltas — down to neighborhood level |
market_berlin_apartment_buildings | Apartment buildings: prices, multiples, transaction volumes |
market_germany_residential | Germany-wide residential price and transaction indices |
market_germany_apartment_buildings | Germany-wide apartment-building price index |
Areas and zoning:
| Tool | What it returns |
|---|---|
berlin_boroughs / berlin_borough_details | The 12 boroughs (Bezirke) |
berlin_districts / berlin_district_details | The 96 districts (Ortsteile) |
berlin_neighborhoods / berlin_neighborhood_search / berlin_neighborhood_details | LOR neighborhoods (Planungsräume) |
berlin_conservation_areas / berlin_conservation_area_details | Social conservation areas (Milieuschutz) |
Socio-demographics (11 tools, socio_berlin_*) — population, age groups, origin, migration, census data on buildings, households, dwellings and rents, construction activity.
Macro indicators (9 tools, macro_*) — ECB policy rates, Bund yields, mortgage lending, construction prices, inflation (HICP), GDP, labor market.
Metadata — field_metadata explains every response field: labels, units, descriptions and data sources, in German and English.
Responses are JSON with German field names (mirroring the underlying data); field_metadata translates them. Prose fields (listing texts, exposé URLs) follow the locale parameter — default en.
About
GUTHMANN® is a Berlin real estate broker. Market Intelligence is our public research area — this server is its machine-readable counterpart.
The server implementation lives in a private monorepo; this repository is the public home of the service: documentation, endpoint and issue tracker.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.