Your own code on a Kubi screen

When the agent is yours, the screen is an API: ask for a screenshot, send actions against the id it came with, run a command, move a file. The SDK is TypeScript; everything else talks to the same HTTP endpoints with a key in the header. One screen or a hundred, the same two calls.

The SDK and the API$20 a screen a month, or $0.035 an hourChecked 2026-11-23

What your own code gains

Written against the API. These three are what change when it has a desktop of its own.

A screenshot you can act against

Every screenshot carries an id. Send it back with your actions and the call is refused if anything moved on the screen in between, so a stale plan cannot click the wrong thing.

Twenty actions in one call

A form is one call, not eight round trips. The reply is the screen after it settles, with the next id, which keeps a loop short and cheap.

Priced by the machine, not the call

A persistent screen is $20 a month at the founding price however many calls you make, and a disposable one is $0.035 an hour billed by the minute. No per-action pricing to model.

Set it up

From a key to the first click.

  1. Step 1

    Make a key

    In the dashboard, open API keys and create one with read and control. It is shown once.

    export KUBI_API_KEY=kubi_...
  2. Step 2

    Install the SDK

    npm install @trykubi/sdk
  3. Step 3

    Look, then act

    import { Kubi } from "@trykubi/sdk";
    
    const client = new Kubi(); // reads KUBI_API_KEY
    const screen = client.screen();
    
    const shot = await screen.screenshot();
    const result = await screen.click({
      x: 640,
      y: 360,
      screenshot_id: shot.screenshot_id,
      screenshot: "after",
    });
  4. Step 4

    Any other language

    Call the API with the same key. Every endpoint is in the reference.

    curl https://api.trykubi.com/v1/screens/scr_.../screenshot \
      -H "Authorization: Bearer $KUBI_API_KEY"

The server's address is https://mcp.trykubi.com. Every app's setup is also in the docs, which is where it is kept current.

The first thing to try

Ask it this

A loop of five steps: screenshot, read the tree, click the element you want by id, type into it, screenshot again. Then open the live view and watch it run.

What to know

  • Write calls take an idempotency key, so a retry after a timeout cannot click twice.
  • Keys carry their own permissions and their own set of screens. Give a script the least of both.
  • The API creates, starts, stops and deletes screens; the MCP server deliberately cannot.

Questions people ask

Is there a Python SDK?

Not yet. Python, Go and everything else use the HTTP API, which is the same surface the SDK calls; the reference has every endpoint with examples.

Can I run my agent on the screen itself?

Yes, and that is the shape for a job that should outlive your laptop: install it on the screen, keep its model key as a secret for that screen, and run it as a service so it comes back after a restart.

How many screens can one key drive?

As many as you give it, up to your organization's cap. A hundred disposable screens for an eval run is the case the by-the-minute price is for.

Read next

The docs carry the detail; these pages carry the price and the choice.

Give your agent a desktop that stays on.

Private beta. Founding price $20 a screen a month, kept while you stay.

Get early access