Background
Danish public data is a goldmine — but it’s hard for AI to use. Statistics Denmark has thousands of datasets, and CVR contains information about every Danish company. But the APIs are complex, and data is returned in formats that consume unnecessary tokens.
My approach
I built MCP servers (Model Context Protocol) that act as intelligent bridges between AI models and Danish data sources. The servers transform and compress data so AI models can work with them efficiently.
DST MCP — Statistics Denmark
- Access to all of Statistics Denmark’s database tables
- Smart transformation reducing tokens by 80-95%
- Metadata caching for fast lookups
CVR MCP — Central Business Register
- Search and look up Danish companies
- 95%+ test coverage
- Structured output optimized for LLM consumption
Results
Both servers are open source and actively used by AI developers in Denmark. They demonstrate how the MCP protocol can make complex data sources accessible to AI — with dramatic reduction in token consumption.
