Title: Danish Data for AI: MCP Servers | Brokk & Sindre Description: Danish public registries such as Statistics Denmark and CVR require complex API calls and return large responses when AI systems use them. Canonical: https://brokk-sindre.dk/en/cases/mcp-servers - [Home](/en) - [Cases](/en/cases) - Mcp servers # Danish Data for AI: MCP Servers Danish public registries such as Statistics Denmark and CVR require complex API calls and return large responses when AI systems use them. By Mikkel Krogsholm · June 1, 2024 AI improves markedly when it can retrieve exactly the right data in a usable form. Access, data quality and cost have to be considered together. - 80-95% token reduction through smart data transformation - 95%+ test coverage on the CVR MCP server - Publicly available as open source on GitHub ## Background Statistics Denmark has thousands of datasets, and CVR contains information about Danish companies. Their APIs require complex calls, and the returned data can consume many unnecessary tokens when an AI system uses it directly. ## My approach I built [MCP](https://modelcontextprotocol.io) 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 public open source. They demonstrate how MCP can give AI systems useful access to complex data sources while reducing token consumption in the measured calls. ## Related cases ### Agent-First API for Real Estate Data Realview wanted to test how AI agents could work directly with its real estate data through a modern, structured interface. ### AI-Powered Concert Company How much of a real concert company can specialized AI agents reliably operate across booking, contracts, marketing, communication and payments? ## Do you face a consequential AI decision? Write about the decision, or ask about a leadership briefing or talk.