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

Chrome Web Store (Recommended)

Install DOMShell directly from the Chrome Web Store. No build step required.

From Source

git clone https://github.com/apireno/DOMShell.git
cd DOMShell
npm install
npm run build

Load into Chrome

1. Open `chrome://extensions/`

2. Enable Developer mode (toggle in top right)

3. Click Load unpacked

4. Select the `dist/` folder

5. Click the DOMShell icon in your toolbar — the side panel opens

Usage

Getting Started

Open any webpage, then open the DOMShell side panel. You'll see a terminal:

╔══════════════════════════════════════╗
║   DOMShell v1.1.0                    ║
║   The browser is your filesystem.    ║
╚══════════════════════════════════════╝

Type 'help' to see available commands.
Type 'tabs' to see open browser tabs, then 'cd tabs/' to enter one.

dom@shell:~$

You start at `~` (the browser root). Jump straight to the active tab with `here`, or explore:

dom@shell:~$ ls
  windows/       (2 windows)
  tabs/          (5 tabs)

dom@shell:~$ here
✓ Entered tab 123
  Title: Google
  URL:   https://google.com
  AX Nodes: 247

Browsing Tabs and Windows

# List all open tabs
dom@shell:~$ tabs
  ID     TITLE                       URL                        WIN
  123    Google                       google.com                 1
  124    GitHub - apireno             github.com/apireno         1
  125    Wikipedia                    en.wikipedia.org                 2

# Switch to a tab by ID
dom@shell:~$ cd tabs/125
✓ Entered tab 125
  Title: Wikipedia
  URL:   https://en.wikipedia.org
  AX Nodes: 312

# You're now inside the tab's DOM tree
dom@shell:~$ pwd
~/tabs/125

# Go back to browser level
dom@shell:~$ cd ~
dom@shell:~$

# Or use substring matching
dom@shell:~$ cd tabs/github
✓ Entered tab 124 (GitHub - apireno)

# List windows (shows tabs grouped under each window)
dom@shell:~$ windows
Window 1 (focused)
├── *123   Google                        google.com
├──  124   GitHub - apireno              github.com/apireno
└──  125   Wikipedia                     en.wikipedia.org

Window 2
├── *126   Stack Overflow                stackoverflow.com
└──  127   MDN Web Docs                  developer.mozilla.org

# Browse a specific window's tabs
dom@shell:~$ cd windows/2
dom@shell:~/windows/2$ ls
  ID     TITLE                       URL
  125    Wikipedia                    en.wikipedia.org
  126    LinkedIn                     linkedin.com

You can also navigate or open new tabs:

# Navigate the current tab to a URL (requires being inside a tab)
dom@shell:~$ navigate https://example.com

# Open a URL in a new tab (works from anywhere)
dom@shell:~$ open https://github.com
✓ Opened new tab
  URL:   https://github.com
  Title: GitHub
  AX Nodes: 412

Tab Groups (isolation)

By default DOMShell operates on your general browser — shared mode, exactly as before. The `group` command puts a session in its own isolated Chrome tab group, so the agent works in a clearly-marked lane while you keep browsing freely in other tabs:

# Create an isolated tab group and work inside it
dom@shell:~$ group new research
✓ Created isolated group '🐚 research'  [id 4]
  Working tab: 312

# While isolated, every command is confined to the group's tabs —
# entering a tab outside the group is rejected:
dom@shell:~$ cd tabs/126
cd: tab 126 is outside the session group (id 4). ...

# Show the current mode and group
dom@shell:~$ group
Group mode: isolated
  Group: 🐚 research  [id 4]
  Tabs:  1

# Leave the group (it stays open) — back to shared mode
dom@shell:~$ group detach

# Close the group's DOMShell tabs (your own tabs are kept)
dom@shell:~$ group close

Subcommands: `group` (status), `group new [name]`, `group attach `, `group detach`, `group close`, `group list`. Isolated mode keeps the agent out of your other tabs; shared mode is the default and unchanged.

When an MCP client connects, DOMShell automatically gives that session its own fresh `🐚 agent` group. The group is left open when the session disconnects (non-destructive) — the agent is instructed to ask whether you'd like it closed before it wraps up, and you can always clear leftovers yourself with `group close`.

Multi-session. Every DOMShell client gets its own session lane — each side-panel window, each MCP connection, separately isolated. Two side panels in two Chrome windows hold independent positions; multiple concurrent MCP agents each work in their own `🐚 agent` group with their own cursor. Run `group list` anytime to see every active lane; `group close ` to close one.

Multiple agents on one MCP connection. Some MCP clients (e.g. Claude Desktop) share one connection across every chat — so by default two chats in the same client would land in one lane. Each chat can carve out its own lane by passing the `group_id` parameter to `domshell_execute`: pass `"new"` to create a fresh one (its id is returned at the end of the reply as `[lane: ]`), then pass that id on every later call. Two chats → two lanes → no collision. Agents can also use this for handoff — one agent reports its lane id, the next agent passes it as `group_id` and continues in the same state. Agents are instructed to close any lane they created when the task is done.

Navigating the DOM

Once you're inside a tab, the Accessibility Tree appears as a filesystem:

# List children of the current node
dom@shell:~$ ls
navigation/
main/
complementary/
contentinfo/
skip_to_content_link
logo_link

# Long format shows type prefixes and roles
dom@shell:~$ ls -l
[d] navigation     navigation/
[d] main           main/
[x] link           skip_to_content_link
[x] link           logo_link

# Filter by type
dom@shell:~$ ls --type link
skip_to_content_link
logo_link

# Show DOM metadata (href, src, id) inline — great for finding URLs
dom@shell:~$ ls --meta --type link
[x] link           skip_to_content_link  href=https://example.com/#content 

# Navigate to parent to find its properties (e.g. span inside a link)
dom@shell:~$ cd ..
dom@shell:~$ cat parent_link

# Bulk extract ALL text from a section (one call instead of 50+ cat calls)
dom@shell:/main$ text
[textContent of /main — 4,821 chars]
Heading: Welcome to Our Site
Today we announce the launch of our new product...
(full article text continues)

# Extract text from a specific child
dom@shell:~$text main
[textContent of main — 4,821 chars]

# Limit output length
dom@shell:~$text main -n 500

# Include link URLs inline as markdown [text](url)
dom@shell:~$text --links main/article/paragraph_2978
--- Text (with links): paragraph_2978 ---
Artificial intelligence (AI) is the capability of [computational systems](https://en.wikipedia.org/wiki/Computer)
to perform tasks typically associated with [human intelligence](https://en.wikipedia.org/wiki/Human_intelligence),
such as [learning](https://en.wikipedia.org/wiki/Learning), [reasoning](https://en.wikipedia.org/wiki/Reason)...
(text + link URLs in a single call)

# Get a tree view (default depth: 2)
dom@shell:~$tree
navigation/
├── [x] home_link
├── [x] about_link
├── [x] products_link
└── [x] contact_link

# Deeper tree
dom@shell:~$tree 4

Searching

# Search current directory
dom@shell:~$grep login
[x] login_btn (button)
[d] login_form (form)
[x] login_link (link)

# Recursive search across all descendants
dom@shell:~$grep -r search
[x] search_search (combobox)
[x] search_btn (button)

# Limit results
dom@shell:~$grep -r -n 5 link

# Deep search with full paths (like Unix find)
dom@shell:~$find search
[x] /search_2/search_search (combobox)
[x] /search_2/search_btn (button)

# Find by role type
dom@shell:~$find --type combobox
[x] /search_2/search_search (combobox)

dom@shell:~$find --type textbox
[x] /main/form/email_input (textbox)
[x] /main/form/name_input (textbox)

# Limit results
dom@shell:~$find --type link -n 5

# Find all links with their URLs (great for content extraction)
dom@shell:~$find --type link --meta
[x] /nav/home_link (link)  href=https://example.com/ 
[x] /main/Read_more (link)  href=https://example.com/article

Command Chaining (Bash-Style Composition)

DOMShell works like a filesystem — use the same mental model as searching files on disk. `grep` discovers where content lives (like `grep -r` in bash), `cd` scopes your context, and `text`/`cat`/`find` reads content (like `cat`/`head`/`less`). The pipe operator (`|`) filters output, just like bash.

The pattern is: grep (locate) → cd (scope) → extract (read).

# Workflow 1: Find and read an article section
dom@shell:~$ grep -r article
[d] article (article)  →  ./main/article/
dom@shell:~$ cd main/article
dom@shell:~/main/article$ text
[full article content in one call]

# Workflow 2: Find a section and extract its links
dom@shell:~$ grep -r references
[d] references (region)  →  ./main/article/references/
dom@shell:~$ cd main/article/references
dom@shell:~/main/article/references$ find --type link --meta
[x] /wiki_link (link)  href=https://en.wikipedia.org/... 
[x] /paper_link (link)  href=https://arxiv.org/... 

# Workflow 3: Find a table and extract structured data
dom@shell:~$ grep -r table
[d] table_4091 (table)  →  ./main/section/table_4091/
dom@shell:~$ extract_table table_4091
| Name   | Value  | Date       |
|--------|--------|------------|
| Alpha  | 42     | 2025-01-15 |
| Beta   | 87     | 2025-02-20 |

# Workflow 4: Discover sections, then drill into one
dom@shell:~$ grep -r heading
[−] Introduction_heading (heading)  →  ./main/article/Introduction_heading
[−] Methods_heading (heading)  →  ./main/article/Methods_heading
[−] Results_heading (heading)  →  ./main/article/Results_heading
dom@shell:~$ cd main/article/Results_heading
dom@shell:~/main/article/Results_heading$ text
[text content of the Results section]

# Workflow 5: Find elements by visible text (not just name)
dom@shell:~$ grep -r --content "sign up"
[x] get_started_btn (button)  →  ./main/hero/get_started_btn
# The button's NAME is "get_started_btn" but its displayed text says "Sign Up Free"
dom@shell:~$ click get_started_btn

Pipe Operator

The pipe operator (`|`) lets you filter command output, just like bash:

# Filter find results to only GitHub links
dom@shell:~$ find --type link --meta | grep github
[x] /main/repo_link (link)  href=https://github.com/example 

# Filter ls output to elements mentioning "login"
dom@shell:~$ ls --text | grep login
[x] login_btn  "Log in to your account"

# Limit results with head
dom@shell:~$ find --type heading | head -n 3
[−] /main/intro_heading (heading)
[−] /main/features_heading (heading)
[−] /main/pricing_heading (heading)

# Chain multiple pipes
dom@shell:~$ find --type link --meta | grep docs | head -n 5

Path Resolution

All commands accept relative paths, eliminating the need to `cd` first:

# Read text from a nested element directly
dom@shell:~$ text main/article/paragraph_2971

# Click a button inside a form without cd'ing
dom@shell:~$ click main/form/submit_btn

# Inspect a link in the nav
dom@shell:~$ cat navigation/home_link

Sibling Navigation

Use `--after` and `--before` flags on `ls` to find content relative to a landmark:

# Show the 3 elements after a heading
dom@shell:~$ ls --after See_also_heading -n 3 --text
[d] related_topics_list  "Machine Learning, Deep Learning, Neural..."
[−] paragraph_4512       "For more information on these topics..."
[x] Read_more_link       "Read more on Wikipedia"

# Find links after a specific section heading
dom@shell:~$ ls --after References_heading --type link --meta
[x] source_1_link (link)  href=https://arxiv.org/... 
[x] source_2_link (link)  href=https://doi.org/...

The key insight: `grep` output feeds `cd`, and `cd` scopes everything else. When you don't know where content lives on a page, always grep first, then scope, then extract.

Interacting with Elements

# Click a button or link
dom@shell:~$click submit_btn
✓ Clicked: submit_btn (button)
(tree will auto-refresh on next command)

# Focus an input field
dom@shell:~$focus email_input
✓ Focused: email_input

# Type into the focused field
dom@shell:~$type hello@example.com
✓ Typed 17 characters

# Navigate to a URL (current tab)
dom@shell:~$navigate https://example.com
✓ Navigated to https://example.com

# Open a URL in a new tab
dom@shell:~$open https://github.com
✓ Opened new tab → https://github.com

Auto-Refresh on DOM Changes

DOMShell automatically detects when the page changes — navigation, DOM mutations, or content updates from clicks. You no longer need to manually run `refresh`:

dom@shell:~$click search_btn
✓ Clicked: search_btn (button)
(tree will auto-refresh on next command)

dom@shell:~$ls
(page changed — tree refreshed, 312 nodes, path reset to tab root)
main/
navigation/
search_results/
...

If the page navigated, CWD is reset to the tab root. If the DOM just updated in place, your CWD is preserved. You can still force a manual refresh:

dom@shell:~$refresh
✓ Refreshed. 312 AX nodes loaded.

Tab Completion

Press `Tab` to auto-complete commands and element names — works like bash:

dom@shell:$ ta
# completes to: tabs

dom@shell:$ cd nav
# completes to: cd navigation/

dom@shell:$ click sub
# if multiple matches, shows options:
#   submit_btn
#   subscribe_link

• Single match: auto-completes inline
• Multiple matches: shows options below, fills the longest common prefix
• `cd` only completes directories; other commands complete all elements

Paste Support

Cmd+V (Mac) / Ctrl+V (Windows/Linux) pastes text directly into the terminal. Multi-line pastes are flattened to a single line.

System Commands

# Check if you're authenticated (reads cookies)
dom@shell:~$whoami
URL: https://example.com
Status: Authenticated
Via: session_id
Expires: 2025-12-31T00:00:00.000Z
Total cookies: 12

# Environment variables
dom@shell:~$env
SHELL=/bin/domshell
TERM=xterm-256color

# Set a variable
dom@shell:~$export API_KEY=sk-abc123

# Debug the raw AX tree
dom@shell:~$debug stats
--- Debug Stats ---
  Total AX nodes:   247
  Ignored nodes:    83
  Generic nodes:    41
  With children:    62
  Iframes:          2

Getting Help

Every command supports `--help`:

dom@shell:$ ls --help
ls — List children of the current node

Usage: ls [options]

Options:
  -l, --long      Long format: type prefix, role, and name
  -r, --recursive Show nested children (one level deep)
  -n N            Limit output to first N entries
  --offset N      Skip first N entries (for pagination)
  --type ROLE     Filter by AX role (e.g. --type button)
  --count         Show count of children only
...

Command Reference

Browser Level

DOM Tree

Automation

System

How the Filesystem Mapping Works

DOMShell maps the browser into a two-level virtual filesystem:

Browser Level (`~`)

The browser itself becomes the top of the filesystem hierarchy:

~                              (browser root)
├── windows/                   (all Chrome windows)
│   ├── /           (tabs in that window)
│   │   ├──            (cd into = enter AX tree)
│   │   └── ...
│   └── ...
└── tabs/                      (flat listing of ALL tabs)
    ├──                (cd into = enter AX tree)
    └── ...

`cd`-ing into a tab transparently attaches CDP and drops you into its DOM tree.

DOM Level (inside a tab)

Each tab's Accessibility Tree (AXTree) is read via the Chrome DevTools Protocol. Each AX node gets mapped to a virtual file or directory:

Directories (container roles): `navigation/`, `main/`, `form/`, `search/`, `list/`, `region/`, `dialog/`, `menu/`, `table/`, `Iframe/`, etc.

Files (interactive/leaf roles): `submit_btn`, `home_link`, `email_input`, `agree_chk`, `theme_switch`, etc.

`cd ..` from the DOM root exits back to the tab listing. `cd ~` returns to browser root from anywhere.

Naming Heuristic

Names are generated from the node's accessible name and role:

Duplicate names are automatically disambiguated with `_2`, `_3`, etc.

Node Flattening

The AX tree contains many "wrapper" nodes — ignored nodes, unnamed generics, and role=none elements that add structural noise without semantic meaning. DOMShell recursively flattens through these, promoting their children up so you see the meaningful elements without navigating through layers of invisible divs.

Iframe Support

DOMShell discovers iframes via `Page.getFrameTree` and fetches each iframe's AX tree separately. Iframe nodes are merged into the main tree with prefixed IDs to avoid collisions, so elements inside iframes appear naturally in the filesystem.

Color Coding

Architecture

┌────────────────────┐
│  Claude Desktop    │──┐
└────────────────────┘  │
┌────────────────────┐  │  HTTP POST/GET/DELETE              ┌─────────────────────┐
│  Claude CLI        │──┼─ localhost:3001/mcp ──┐            │  Side Panel (UI)    │
└────────────────────┘  │  (Bearer token auth)  │            │                     │
┌────────────────────┐  │                       │            │  React + Xterm.js   │
│  Cursor / Other    │──┘                       │            │  - Paste support    │
└────────────────────┘                          ▼            │  - Tab completion   │
                               ┌─────────────────────┐      │  - Command history  │
                               │  MCP Server          │      └─────────┬───────────┘
                               │  (mcp-server/)       │                │
                               │                      │       chrome.runtime
                               │  Express HTTP server  │       .connect()
                               │  Per-session MCP      │                │
                               │  Security layer:     │      ┌─────────▼───────────┐
                               │  - Auth token        │      │  Background Worker  │
                               │  - Command tiers     │      │   (Shell Kernel)    │
                               │  - Domain allowlist  │      │                     │
                               │  - Audit log         │      │  Browser hierarchy  │
                               └──────────┬───────────┘      │  (~, tabs, windows) │
                                          │                  │  Command parser     │
                               WebSocket (localhost:9876)     │  Shell state (CWD)  │
                               + auth token                  │  VFS mapper         │
                               + alarm keepalive             │  CDP client         │
                                          │                  │  DOM change detect  │
                                          └─────────────────►│  WebSocket bridge   │
                                                             └─────────┬───────────┘
                                                                       │
                                                              chrome.debugger
                                                              (CDP 1.3)
                                                                       │
                                                             ┌─────────▼───────────┐
                                                             │   Active Tab        │
                                                             │   Accessibility     │
                                                             │   Tree + iframes    │
                                                             │                     │
                                                             │   DOM events ──────►│
                                                             │   (auto-refresh)    │
                                                             └─────────────────────┘

The MCP server runs as a standalone HTTP service that any number of MCP clients can connect to simultaneously. It exposes two ports: an HTTP endpoint for MCP clients (default 3001) and a WebSocket bridge for the Chrome extension (default 9876).

The extension follows a Thin Client / Fat Host model. The side panel is a dumb terminal — it captures keystrokes, handles paste, and renders ANSI-colored text. All logic lives in the background service worker: command parsing, AX tree traversal, filesystem mapping, CDP interaction, browser hierarchy navigation, and DOM change detection.

Source Layout

src/
  background/
    index.ts        # Shell kernel — commands, state, message router, auto-refresh, WS bridge
    cdp_client.ts   # Promise-wrapped chrome.debugger API + iframe discovery
    vfs_mapper.ts   # Accessibility Tree → virtual filesystem mapping
  sidepanel/
    index.html      # Side panel entry HTML
    index.tsx        # React entry point
    Terminal.tsx     # Xterm.js terminal (paste, tab completion, history)
  shared/
    types.ts        # Message types, AXNode interfaces, role constants
public/
  manifest.json     # Chrome Manifest V3
  options.html      # Extension settings page (MCP bridge config)
mcp-server/
  index.ts          # MCP server — standalone Express HTTP + StreamableHTTP, WebSocket bridge, security
  proxy.ts          # Stdio↔HTTP bridge for clients that require command/args (e.g. Claude Desktop)
  package.json      # MCP server dependencies
  tsconfig.json     # MCP server TypeScript config

Tech Stack

• React + TypeScript — Side panel UI
• Xterm.js (`@xterm/xterm`) — Terminal emulator with Tokyo Night color scheme
• Vite — Build tooling with multi-entry Chrome Extension support
• Chrome DevTools Protocol (CDP 1.3) via `chrome.debugger` — AX tree access, element interaction, iframe discovery, DOM mutation events
• Chrome Manifest V3 — `sidePanel`, `debugger`, `activeTab`, `cookies`, `storage`, `alarms` permissions

Development

# Watch mode (rebuilds on file changes)
npm run dev

# One-time production build
npm run build

# Type checking
npm run typecheck

After building, reload the extension on `chrome://extensions/` and reopen the side panel to pick up changes.

Connecting MCP Clients (Claude Desktop, CLI, Cursor, etc.)

DOMShell includes a hardened MCP server that lets any MCP-compatible client control the browser through DOMShell commands. The server runs as a standalone HTTP service — multiple clients can connect simultaneously.

Three install paths

DOMShell's MCP server supports three install paths — pick whichever matches your setup. Path 1 is the documented default and what most users want. Paths 2 and 3 are optional and exist for users who want container isolation or lifecycle management.

Full Path 2 / Path 3 instructions (build, `.env` install pattern, launchd autostart template, reboot recovery): **`docs/deploy/container-and-toolhive.md`**. The rest of this README covers Path 1 — the simplest and recommended default.

Install via npm (Path 1 — default)

npm install -g @apireno/domshell

Or run directly without installing:

npx @apireno/domshell --allow-write --token my-secret-token

Architecture

User starts independently:
  npx @apireno/domshell --allow-write --token xyz
    → HTTP on :3001/mcp  (MCP clients)
    → WebSocket on :9876  (Chrome extension)

Claude Desktop spawns (stdio proxy):                    ┐
  npx domshell-proxy --port 3001 --token xyz            ├─► HTTP :3001/mcp
Claude CLI connects directly:                           │
  url: http://localhost:3001/mcp?token=xyz              │
Gemini CLI connects directly:                           │
  url: http://localhost:3001/mcp?token=xyz              ┘

The MCP server is a standalone HTTP service — you start it independently, and any number of MCP clients connect to it. No single client "owns" the server process. For clients that require stdio (like Claude Desktop), a tiny proxy bridges stdio to the running HTTP server.

Setup

Quick setup (recommended):

npx @apireno/domshell init

The wizard detects installed MCP clients (Claude Desktop, Cursor, Windsurf), generates a shared token, and writes each client's config. You then start the server once in a terminal — all clients connect to it.

Use `--yes` for non-interactive mode with sensible defaults:

npx @apireno/domshell init --yes

Manual setup:

1. Start the MCP server:

npx @apireno/domshell --allow-write --token my-secret-token

The server starts two listeners:

• HTTP on `http://127.0.0.1:3001/mcp` — MCP client endpoint
• WebSocket on `ws://127.0.0.1:9876` — Chrome extension bridge

> Tip: Use `--token` to set a known token so you can pre-configure clients. If omitted, a random token is generated and printed on startup.

2. Connect MCP clients:

Claude CLI / Gemini CLI / Cursor (direct HTTP — recommended):

http://localhost:3001/mcp?token=my-secret-token

Claude Desktop (requires stdio — use the proxy):

Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):

{
  "mcpServers": {
    "domshell": {
      "command": "npx",
      "args": ["-y", "@apireno/domshell", "--allow-write", "--token", "my-secret-token"]
    }
  }
}

Restart Claude Desktop. DOMShell tools will appear.

3. Connect the extension (Options Page):

1. Go to `chrome://extensions/`

2. Find DOMShell and click Options (or right-click the extension icon → Options)

3. Enable the MCP Bridge toggle

4. Paste the same token you used in the Claude Desktop config (`my-secret-token`)

5. Click Save — the status indicator turns green when connected

The options page shows live connection status: Disabled, Connecting, Connected, or Disconnected.

Alternative: Connect via terminal

You can also connect from the DOMShell terminal instead of the options page:

dom@shell:$ connect my-secret-token

4. Test it:

Ask Claude: *"List my open tabs and tell me what's on the first one."*

Security

The MCP server is hardened with multiple layers of security. By default, it's read-only — Claude can browse but not click or type.

Command Tiers

The Navigate tier is separate from Write because navigation is equivalent to typing a URL — it requires `--allow-write` but skips the interactive confirmation prompt. This is important for Claude Desktop where `/dev/tty` is unavailable.

Security Flags

Per-Action Confirmation (opt-in)

Per-action terminal prompts are off by default — the MCP server's terminal is detached from where the agent and side panel actually run, so the prompt is awkward to answer in any GUI-spawned setup (Claude Desktop, Cursor, CLI-Anything's harness). The audit log captures every command, and the tier flags (`--allow-write`, `--allow-sensitive`) plus `--domains` remain the actual security boundaries.

If you start the server in your own terminal and want a y/n prompt before every write, add `--confirm`:

[DOMShell] Claude wants to: click submit_btn
Allow? (y/n):

`--no-confirm` is preserved as a no-op (it matches the default), so any existing config that passes it keeps working unchanged.

Auth Token

• Use `--token` to set a known token in the MCP server config, or let the server generate a random one on startup
• The extension must present this token (via the options page or `connect `) before the bridge works
• WebSocket connections without a valid token are rejected
• Token is stored in `chrome.storage.local` — survives service worker restarts

Domain Allowlist

With `--domains`, commands are only executed when the active tab's URL matches:

npx tsx index.ts --allow-write --domains "github.com,docs.google.com"

Audit Log

Every command is logged with timestamps to `audit.log` (or `--log-file`):

[2026-02-07T12:00:00.000Z] EXECUTE: ls -l
[2026-02-07T12:00:01.000Z] RESULT: 12 items
[2026-02-07T12:00:05.000Z] [WRITE] EXECUTE: click submit_btn
[2026-02-07T12:00:05.500Z] [WRITE] RESULT: ✓ Clicked: submit_btn (button)

Disconnecting

Disable the MCP Bridge toggle in the extension options page, or run `disconnect` in the DOMShell terminal:

dom@shell:$ disconnect
✓ Disconnected from MCP server.

The `domshell_execute` interface

DOMShell's MCP server exposes a single tool by default — `domshell_execute` — the recommended way to drive DOMShell. You pass a command string, exactly as you would type it in the DOMShell terminal:

domshell_execute("ls")
domshell_execute("cd tabs/4815")
domshell_execute("find --type link --meta")

Multi-command calls. Pass several commands separated by newlines and they run in sequence, with the combined output returned — a whole workflow in one tool call:

domshell_execute("open https://example.com
cd main
text")

One round-trip instead of three, and fewer tool-call cycles.

Multi-line semantics. Each line runs in order in the same MCP session and lane, so `cwd`, env, and history persist between lines (the second line's `cd main` is relative to the first line's freshly-opened tab). An error on any single line does not halt the rest — its error message is included in the combined output and subsequent lines still run. That's the right shape for cleanup-line idioms like `"cd path\ngrep pattern\ncd back"` where the trailing restore must run even if the middle step errors. Implementation: `mcp-server/index.ts:1115-1136`.

Two modes:

Start the server with `--granular` for the per-command tools:

npx @apireno/domshell --granular

Security is identical in both modes. DOMShell's server-side tiers (`write` / `sensitive` — set by `--allow-write`, `--allow-sensitive`, with optional `--confirm` for per-action server-terminal prompts) gate risky operations regardless of which tool issued the command. Granular mode does not add security — it adds an extra *approval prompt* in your MCP client per operation type. That's more human oversight, not more protection.

MCP Tools Reference (`--granular` mode)

The table below lists the per-command tools exposed when the server runs with `--granular`. In the default single-tool mode, run the same commands through `domshell_execute` — the `Maps To` column shows the command string.

Roadmap

Distribution & Setup

• [x] Chrome Web Store listing — live on the Chrome Web Store
• [x] GitHub release with .crx — v1.1.1 release with extension zip
• [x] MCP setup wizard — `npx @apireno/domshell init` detects installed MCP clients, generates a token, and writes the config automatically
• [ ] Support for other MCP clients — Gemini Desktop, OpenAI ChatGPT desktop, Cursor, Windsurf, and other MCP-compatible hosts

New Commands

• [x] `watch` — periodic re-execution of a command (e.g. `watch ls --times 3 --interval 1` to poll for DOM changes)
• [x] `history` — command history with recall (`history`, `!n` to re-run)
• [x] `back` / `forward` — browser-style history navigation within the current tab
• [x] `close` — close the current tab (`close` or `close `)
• [x] `screenshot` — capture a screenshot of the current tab (useful for visual verification alongside AX tree inspection)
• [x] `pipe` / `|` — pipe output between commands (e.g. `find --type link | grep login`)
• [x] `select ` — select an option from a `` dropdown by value or visible text
• [x] `scroll` — scroll the page or a specific element (`scroll down`, `scroll up`, `scroll `)
• [x] `wait` — wait for a specific element to appear (e.g. `wait submit_btn` blocks until it exists in the tree)
• [x] `for` loop — iterate over command output lines (e.g. `for "find --type heading -n 3" : text {}`) — replaces manual iteration
• [x] `script` command — save and run multi-command scripts (e.g. `script save scrape open url ; cd main ; text`) for repeatable workflows

JavaScript Layer

• [x] `js` command — execute arbitrary JavaScript in the tab context and return the result
• [x] `functions` + `call` — `functions [pattern]` lists callable global JS functions with name/arity/params; `call funcName arg1 arg2` invokes them. `call` is write-tier.
• [x] `eval ` — quick expression evaluation (e.g. `eval document.title`, `eval window.location.href`)

Agent Ergonomics

• [x] `--text` flag — show visible text previews inline with `ls` and `find` using `.innerText` (rendered text only, respects CSS visibility); configurable length via `--textlen N`; `cat` also shows VisibleText separately from textContent
• [x] `--meta` flag — show DOM properties (href, src, id, tag) inline with `ls`, `find`, and `read` output — essential for extracting URLs without separate `cat` calls
• [x] `--content` matching — search by visible text content with `grep --content` and `find --content` (or `find --text "pattern"`) — finds elements by what they display, not just their AX name
• [x] Path resolution — all commands accept relative paths (e.g. `text main/article/paragraph`, `click form/submit_btn`) — eliminates unnecessary `cd` round-trips
• [x] Sibling navigation — `--after`/`--before` flags on `ls` to slice children relative to a landmark element (e.g. `ls --after heading --type link --meta`)
• [x] `--links` flag on `text` — include hyperlink URLs inline as markdown `text` in text output; extracts both content and link destinations in a single call (e.g. `text --links main/paragraph`)
• [x] Fuzzy type aliases for `find` — `find --type` accepts natural-language aliases (input, dropdown, nav, toggle, modal, image, btn, sidebar, etc.) that expand to matching AX roles — eliminates wasted tool calls from guessing exact role names
• [x] Visible text cache — lazy cache for `innerText` results, keyed by `backendDOMNodeId`, cleared on tree rebuild — eliminates redundant CDP calls during `--content` matching in `grep`/`find`
• [x] `bookmark` / `alias` — save named paths for quick navigation (e.g. `bookmark inbox ~/tabs/gmail/main/inbox_list`, `cd @inbox`)
• [x] `each` (multi-tab) — run a command across multiple tabs (e.g. `each --pattern wiki text` to extract text from every Wikipedia tab)
• [x] Structured output mode — `--json` flag on commands for machine-parseable output (e.g. `ls --json`, `cat --json`, `find --json`, `diff --json`)
• [x] Session persistence — save and restore shell state (path, env vars, bookmarks, history) across service worker restarts via `chrome.storage.local`
• [x] `diff` — compare AX tree snapshots to see what changed after an action (auto-snapshots before click/submit/navigate)
• [ ] Session tab-group isolation — each session's tabs are placed in a labeled Chrome tab group and every command is confined to that group, so the agent works in its own lane while you keep browsing freely in other tabs of the same window (#32)
• [ ] Multi-session DOMShell — every side-panel console and every MCP connection gets its own independent shell session (its own current directory, tab, and DOM cursor), so multiple human consoles and concurrent agents each work in an isolated lane instead of sharing one global cursor (#33)
• [ ] Agent-declared sessions — an optional `group_id` on `domshell_execute` lets an agent address a specific lane: omit it for the current lane, `"new"` for a fresh one, or pass an id to join an existing lane — so two agent chats sharing one MCP connection stay isolated, and one agent can hand a session off to another (#34)

Platform

• [ ] Standalone headless browser — ship DOMShell as a self-contained headless Chromium process (via Chrome for Testing or embedded Chromium) that agents launch directly — no extension install, no user Chrome profile; just `npx @apireno/domshell --headless` and connect via MCP. Ideal for CI pipelines, server-side automation, and agent-in-a-loop workflows where a visible browser isn't needed
• [ ] Firefox extension — port to Firefox using WebExtensions API + remote debugging protocol
• [ ] Playwright/Puppeteer backend — alternative to Chrome extension for headless agent workflows
• [ ] REST API mode — expose DOMShell commands over HTTP for non-MCP integrations
• [ ] WASM build — compile DOMShell to WebAssembly so it can be embedded directly on a website for interactive demos without requiring a Chrome extension install

Experiments

• [x] Nexa: DOMShell vs Raw HTML — same model (Qwen3-4B), same tasks: compare DOMShell's text/AX-tree interface against raw HTML scraping. Tests on both nexa serve and Ollama backends. Found a crossover interaction: Ollama+DOMShell and Nexa+HTML are equally best (1.20 avg). See `experiments/nexa_ollama/`.
• [x] Nexa vs Claude (model size) — compared Qwen3-1.7B/4B on progressive tasks. Capability cliff at T3 (paragraph extraction). 4B shows better error recovery. See `experiments/nexa_claude/`.
• [x] Model shootout — compared Qwen3-4B, Hermes3-3B, Granite4-Tiny, Llama3.2-3B on Ollama+DOMShell. Qwen3-4B remains best (8/15), only model to break the T3 cliff. Llama3.2-3B close second (7/15, zero hallucinations). See `experiments/model_shootout/`.
• [ ] Token cost benchmark — measure total input/output tokens per task across DOMShell vs screenshot-based browsing (CiC). Extend existing `experiments/claude_domshell_vs_cic/` with token counting. Hypothesis: structured text (2-3KB per response) vs base64 screenshots (500KB+) should show >2x token savings on top of the 2x call-count reduction already measured

Integrations

Nexa AI (Local LLM)

Run DOMShell with local models via nexa-sdk — fully on-device browser automation with no cloud API needed. Uses the same MCP protocol as Claude Desktop but powered by local inference (Granite-4-Micro, Qwen3, etc.).

python integrations/nexa/agent.py --task "Open wikipedia.org/wiki/AI and extract the first paragraph" --verbose

See integrations/nexa/ for setup and usage.

How This Project Was Built

The technical specification for DOMShell was authored by Google Gemini, designed as a comprehensive prompt that could be handed directly to a coding agent to scaffold and build the entire project from scratch. The full original specification is preserved in `intitial_project_prompt.md`.

The implementation was then built by Claude (Anthropic) via Claude Code, working from that specification.

An AI-designed project, built by another AI, intended for AI agents to use. It's agents all the way down.

Links

• Chrome Web Store
• npm: @apireno/domshell
• MCP Server Registry
• mcpservers.org
• Glama
• Blog: Why I Built a Filesystem for the Browser
• Project home & privacy policy
• Built by Pireno

License

MIT