Build dashboards with your AI agent
[⏱️ ~2 min] Point Cursor or Claude at MDK and build mining dashboards from plain-language prompts
MDK is built so your AI coding agent can build mining dashboards straight from plain-language prompts, without you wiring components by hand. There are two steps: wire your IDE once, then describe what you want.
Wire your IDE once
Run init
Point the UI CLI at your IDE from your project root:
npx @tetherto/mdk-ui-cli init --ide cursorUse --ide claude for Claude. This writes a .mdk/context.md agent-context file and an IDE rule (.cursor/rules/mdk.mdc for
Cursor, CLAUDE.md for Claude) so every AI session knows about MDK automatically.
Prompt your agent
Describe the dashboard you want in plain language:
Build me an operations dashboard with live hashrate and a device list.
Your agent takes it from there: it finds the right components and hooks, scaffolds the page, and checks that it compiles. You review and run it.
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
You do not need any of this to use the tooling, it is here to explain why the results are trustworthy.
Build any dashboard (example walkthrough)
MDK is not mining-only. This concept page replays the same agent flow above and ships a statistics lab dashboard with charts, tables, and mock data.
Next steps
- UI CLI reference: every command your agent (or you) can run
- Ship a dashboard fast: wire the React packages by hand
- UI Kit: browse the component library your agent draws from
- AI agents and the MCP Server: runtime path for live fleet control