How agents build with MDK
Why an AI coding agent can build MDK dashboards from a prompt without hallucinating components — the local manifests and stable-export contract behind the flow
MDK is built so your AI coding agent can turn a plain-language prompt into a working dashboard, without you wiring components by hand. This page explains why those results are trustworthy — the build-time flow an agent follows on your machine. For the setup steps, see Build dashboards with your AI agent. For the runtime path where agents drive a live fleet, see AI agents and the MCP Server.
What your agent does for you
Behind a single prompt, the agent:
- Finds the right MDK components and hooks for your intent
- Wires real adapter hooks and state, with no guessed imports or props
- Scaffolds a page and verifies that it compiles
- Reaches for stable, supported components by default, so the result is something you can ship
The outcome: the agent pulls real metadata, real examples, and real types instead of hallucinating an API.
How it works
MDK ships a small set of machine-readable files that describe every component, hook, and store. Your agent reads those local files, makes no network or model calls of its own to discover them, and only reaches for exports that MDK marks as stable. Because it works from generated metadata rather than guesswork, it does not invent props or imports.
For the full command surface those manifests power, see the UI CLI reference. The complete contract that keeps the metadata honest lives in the MDK repositories.
Next steps
- Build dashboards with your AI agent: the two-step setup flow
- Build a dashboard with an agent: a full Stats Lab walkthrough with the UI CLI commands
- UI CLI reference: every command your agent (or you) can run
- AI agents and the MCP Server: the runtime path for live fleet control