Background
Realview operates Denmark’s largest and most widely used real estate database. Banks, mortgage companies and real estate agents use it daily for valuation, credit assessment and market analysis. They had an existing API for their customers, but it was not built for the world we are moving into — a world where AI agents need to query data, analyze and report independently.
Realview wanted to test what happens when you give agents direct access to real estate data. And they needed a modern API to build it on.
What I built
I built a complete API in FastAPI with MCP (Model Context Protocol) designed in from the start. Not as an add-on, but as a foundation — agent-first.
Tech stack
- FastAPI for the API itself
- MCP (Model Context Protocol) for agent access
- Realview’s database as the data source
It took two days. A fully functional API with endpoints, documentation and an MCP server that AI agents can talk to. This would normally have taken several weeks with a traditional approach.
Results
After launch, we tested the MCP server by having AI agents run advanced analyses and reports directly on Realview’s housing data. Agents that fetch data, process it and deliver insights on their own — without a human manually pulling numbers.
That is the difference between having data and having data that works for you.
