# Web Draw: Drive the live browser as compact text, without screenshots

> Source: <https://dev.to/olib_ai/web-draw-drive-the-live-browser-as-compact-text-without-screenshots-ho>
> Published: 2026-09-02 22:38:05+00:00

Most tools that let AI agents browse the web work by taking screenshots of the page. That approach burns thousands of tokens per action, runs slowly, and leaves the model guessing pixel coordinates to click.

We built Web Draw to solve this. It is a free Chrome extension paired with a local MCP server that lets any LLM agent read and drive the tab you already have open, as compact text instead of pixels.

Web Draw reads the visible DOM and turns it into structured text with a stable handle on every button, link, and input:

```
[search]
e4 searchbox "Search Amazon" ="usb c hub"
[form]
e29 combobox "Sort by:" ="Featured"
e49 button "Add to cart"
off-screen: 37 controls below, next "Popular Shopping Ideas"
```

The agent acts directly on a handle (like clicking e49 or typing into e4) instead of guessing coordinates.

Web Draw exposes five tools to your agent:

Install the extension from the Chrome Web Store:

[https://chromewebstore.google.com/detail/web-draw-by-olib-ai/goknikkadndlonalcpjmnfpnljdehaim?authuser=0&hl=en](https://chromewebstore.google.com/detail/web-draw-by-olib-ai/goknikkadndlonalcpjmnfpnljdehaim?authuser=0&hl=en)

Add Web Draw to your MCP client (Claude Desktop, Claude Code, Cursor, or any agent supporting MCP):

```
"web-draw": {
  "command": "npx",
  "args": ["-y", "@olib-ai/web-draw-mcp"]
}
```

Once running, the extension toolbar badge switches to ON, and your agent can read and drive the active tab.