Happy slice of mcp pizzaMCP.pizza

DOMShell

MCP.Pizza Chef: apireno

DOMShell turns your Chrome browser into a navigable filesystem accessible via terminal commands. Inside apps like Claude Desktop or ChatGPT, you can list open tabs, read webpage content, click buttons, and open new tabs—all by typing simple commands. It requires no API keys and installs easily via the Chrome Web Store or npm. This lets your AI assistant interact with websites precisely and reliably, without fragile scraping or guesswork.

Other
Web/Research

Use This MCP server To

Browse open browser tabs and windows via terminal commands Read and extract webpage content as text files Click buttons and interact with page elements using commands Open new URLs in new browser tabs from the terminal Navigate the browser's page structure like a filesystem Isolate browsing sessions in separate tab groups for focused work Search for page elements by type using simple commands

README

DOMShell

           | |
        ___|_|___
       |___|_|___|
       |   | |   |
       |___|_|___|
        /  | |  \
       /   | |   \
      |____|_|____|
      |           |
      |  DOMSHELL |
      |           |
      |___________|
      |###########|
      |###########|
       \#########/
        \_______/
 
  ██   ██ ██ ███████
  ██   ██ ██   ███
  ███████ ██   ██
  ██░░░██ ██   ██
  ██   ██ ██   ██
  ░░   ░░ ░░   ░░
   ███████ ██   ██ ███████
     ███   ███████ ██░░░░░
     ███   ██░░░██ █████
     ███   ██   ██ ██░░░
     ███   ██   ██ ███████
     ░░░   ░░   ░░ ░░░░░░░
   ██████   ██████  ███    ███  ██
   ██   ██ ██    ██ ████  ████  ██
   ██   ██ ██    ██ ██ ████ ██  ██
   ██   ██ ██    ██ ██  ██  ██  ░░
   ██████   ██████  ██      ██  ██
   ░░░░░░   ░░░░░░  ░░      ░░  ░░

The browser is your filesystem. A Chrome Extension that lets AI agents (and humans) browse the web using standard Linux commands — ls, cd, cat, grep, click — via a terminal in the Chrome Side Panel.

Install from Chrome Web Store | npm package | Read the blog post | Project home

DOMShell maps the browser into a virtual filesystem. Windows and tabs become top-level directories (~). Each tab's Accessibility Tree becomes a nested filesystem where container elements are directories and buttons, links, and inputs are files. Navigate Chrome the same way you'd navigate /usr/local/bin.

Why

AI agents that interact with websites typically rely on screenshots, pixel coordinates, or brittle CSS selectors. DOMShell takes a different approach: it exposes the browser's own Accessibility Tree as a familiar filesystem metaphor.

This means an agent can:

  • Browse tabs with ls ~/tabs/ and switch with cd ~/tabs/123 instead of guessing which tab is active
  • Explore a page with ls and tree instead of parsing screenshots
  • Navigate into sections with cd navigation/ instead of guessing coordinates
  • Act on elements with click submit_btn instead of fragile DOM queries
  • Read content with cat or bulk-extract with text instead of scraping innerHTML
  • Search for elements with find --type combobox instead of writing selectors

The filesystem abstraction is deterministic, semantic, and works on any website — no site-specific adapters needed.

Installation

DOMShell FAQ

Can I use DOMShell to navigate and interact with web pages using commands?
Yes — DOMShell lets you browse tabs, read page content, and click buttons via simple terminal commands inside supported apps like Claude Desktop and ChatGPT.
Can I use DOMShell to open new browser tabs or switch between tabs?
Yes — you can open URLs in new tabs and switch tabs by ID or name using command-line instructions.
Which apps support DOMShell?
DOMShell works with Claude Desktop, ChatGPT, Cursor, and Windsurf, providing a terminal interface inside these apps.
Do I need an API key or special account to use DOMShell?
No — DOMShell requires no API key or account; it runs as a Chrome extension or via npm package.
How difficult is it to set up DOMShell?
Setup is easy — you can install it with a simple copy-paste config or from the Chrome Web Store with one click.