Traycer vs Kiro (building an mcp app with both)

You’ve probably have heard of MCP servers by now. If not, they are a way to connect AI agents to your tools: files, databases, calendars, whatever. They are plugins but for agents. MCP apps take it one step further. They come with a user interface. The agent does work in the background, and shows you something visual. Watch this short video if you want to see how mcp apps look like. In this case, I built the same MCP mind-mapping app twice: once with Traycer, once with Kiro. Both are spec-driven development tools (a term I will explain in a second). First: What Is Spec-Driven Development? You've probably also heard of vibe coding.. the thing where you just describe what you want to an AI, watch it write code, and fix things as they break. It feels fast and often works for small stuff. But on anything complex, it turns into chaos pretty quickly. Spec-driven development is the opposite approach. Before you write a single line of code, you write specs — structured Markdown files that desc