# MCP server

> One URL gives an agent app its own desktop. No code, nothing to install.

Kubi runs a hosted MCP server with the API. Add one URL to Claude Code, claude.ai, Claude Desktop, Codex, Cursor or VS Code, sign in, and the agent can see a screen, click and type on it, run commands and move files:

```text
https://mcp.trykubi.com
```

It speaks MCP's Streamable HTTP transport. It runs inside our API, so there is nothing to install or keep running on your side.

## MCP, the SDK or the API

All three reach the same screens, with the same rules and the same history.

| You have | Use |
|---|---|
| An agent app: Claude Code, claude.ai, Codex, Cursor, VS Code | The MCP server |
| Your own code in TypeScript | The [TypeScript SDK](/sdk/typescript) |
| Your own code in any other language | The [API](/api) |

## How a session goes

1. The agent calls `screenshot` and gets the screen as an image with its `screenshot_id`.
2. It calls `act` with up to 20 actions and that `screenshot_id`. Actions go by point, or by an element id from `read_tree`.
3. The reply carries the screen after the actions, with a new `screenshot_id` for the next step. One call is one step.
4. If anything ran on the screen since the screenshot, a person included, the actions don't run and the agent gets `STALE_OBSERVATION`: it looks again. The full loop: [The look and act loop](/concepts/look-and-act).

The server's instructions are a short guide to that loop, and `guide` answers more by topic. `read_tree` with `window: "all"` finds an element in any window, `apps` lists apps for `act`'s `launch`, `page` reads and fills a browser tab by ref, and `run_script` runs a GUI script inside the screen for loops in one call. Besides that loop, `exec` runs shell commands, `read_file` and `write_file` move files, `clipboard` reads or sets the clipboard, and `viewer_link` gives a person a live view of the screen.

## What it never does

The MCP server has no tools to create or delete screens, make keys or touch billing. Those stay in the dashboard, for people. Starting, stopping and restarting a screen aren't offered yet either; do them in the dashboard or through the API.

## In this section

- [Connect](/mcp/connect): the setup for each agent app, or an API key instead.
- [Sign-in and permissions](/mcp/sign-in): what you grant, for how long, and how to take it back.
- [Tools](/mcp/tools): every tool, with its inputs, read from the server itself.
- [Errors and limits](/mcp/errors-and-limits): what a failed call says, and the sizes and times to plan for.
