Most teams shipping AI to production are still building on a stack designed for 2023. Custom chat UIs. Orchestration frameworks. RAG pipelines. Vector databases. Agent observability layers. An AI platform team to keep it all running. At Warmtebouw we skipped all of it and shipped nine MCP servers in three months for non-technical business users across ERP, BIM, fleet, energy, and operational systems.
This is the case that MCP isn't a piece of your AI platform — it is your AI platform, and most of the layers above it are overhead you don't need at mid-market scale.
The model is the agent. The framework is overhead.
The framing "you need an agent framework" obscures a simpler truth: the model is the agent. It reads tool descriptions. It chooses which tool to call. It sequences the calls. It interprets the results. That's textbook agentic behaviour, built into every frontier model that speaks MCP.
What companies sell you on top of that is framework around the agent: orchestration logic, retrieval pipelines, prompt managers, observability layers. Each of those products is solving a real problem in some context. But in a mid-sized business with a knowable set of important data sources, those contexts mostly don't apply.
