Agency partnerships in Germany · Use case

Where should my brokerage open or grow next in Germany?

Run AgentGraph AI's agentgraph_territory_map on the Casafari MCP server for a German state, district or city. It returns one row per district or municipality with active homes, exits in 12 months, number of brokers, per-broker ratios, franchise and independent shares, your own network's share, top networks, a centre point and an opportunity score to rank where to grow.

Products: AgentGraph AI

#Short answer

agentgraph_territory_map returns one row per district or municipality of a German region (state, district or city). Each row has active homes, exits in 12 months, number of brokers, exits and active homes per broker, the share held by franchise networks and by independents, your own network's share, the top networks, a centre point for drawing a map, and an opportunity score. Use it to decide where to open or grow next, then screen partners in the best areas. It is part of AgentGraph AI, MCP only.

Expansion decisions made on measured broker density and demand, district by district, cost far less than offices opened on instinct.

#Steps

#Resolve the region: agentgraph_find_location

1. Call agentgraph_find_location with query (for example "Bayern") to get the location id, kind and parent areas. Skip this when the name is unambiguous; the map also takes a name.

#Map: agentgraph_territory_map with location, operation and client_brand

2. Call agentgraph_territory_map with location (required), operation (sale by default, or rent) and client_brand, your own network's name, so the map can show your share.

#Benchmark the best rows: agentgraph_area_benchmark with unit agency or agent

3. For the districts that stand out, call agentgraph_area_benchmark with location, unit (agency, the default, or agent) and operation. It returns percentiles of active homes, exits, days on market, price cuts and momentum, the split between independents, franchises, banks and online brokerages, and the biggest networks.

#Screen partners there: agentgraph_screen_agencies

4. Call agentgraph_screen_agencies with the chosen district as location (or its postcodes in zipcodes), the profiles you want and the same client_brand, to find agencies worth partnering with or acquiring there.

#Example: Bayern

Prompt to your AI assistant:

Map Bayern and tell me where independents hold the market.

The assistant calls agentgraph_territory_map with arguments like these:

{
  "location": "Bayern",
  "operation": "sale",
  "client_brand": "(your network)"
}

It sorts the rows by independent share and opportunity score. A condensed table looks like this (placeholders shown; the tool returns the real rows):

It then runs agentgraph_area_benchmark for the top rows and, if asked, agentgraph_screen_agencies there.

#How to read the result

#Opportunity score and its inputs

The opportunity score ranks rows for expansion. The tool description does not publish how the score is weighted, so read it together with its row's inputs: exits in 12 months show market activity, brokers and per-broker ratios show how crowded the market is, and the franchise and independent shares show who holds it. A high score in a district with high exits per broker points to demand served by few brokers.

#Your own network's share versus the top networks

With client_brand set, each row shows your network's share next to the top networks. Rows where you are absent but independents hold much of the market suit recruiting independents; rows dominated by one network suggest a harder entry.

#Percentiles from the benchmark: what normal looks like

agentgraph_area_benchmark shows what normal looks like for brokers in a chosen area. Use its percentiles to judge whether a district's brokers are unusually productive or slow, and to set thresholds such as min_exits_last_12m when you screen agencies there.

#Limits

AgentGraph AI tools are available to Casafari clients with MCP access, using their Casafari account; self-serve access for new users is coming soon. They are MCP only, with no REST equivalent. The sources give no prices, quotas, rate limits or SLAs; ask Casafari.

#Germany only

AgentGraph AI covers Germany. The map takes a German state, district or city; see Does Casafari cover Germany?.

#Figures are derived from the properties brokers advertise

The map is built from the properties brokers advertise, counted as properties in the property graph. Business a broker does without advertising it does not appear, and the map does not cover closed sale prices.

#Questions

All use cases