Browser Use
Lets AI do web tasks for you, such as filling forms, searching and extracting data, in the maker’s cloud browsers or on your computer.
Description from the maker (original English)
Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"domshell": {
"command": "npx",
"args": [
"-y",
"@apireno/domshell"
]
}
}
}Run this in your terminal
claude mcp add domshell -- npx -y @apireno/domshellPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"domshell": {
"command": "npx",
"args": [
"-y",
"@apireno/domshell"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"domshell": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@apireno/domshell"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account apireno, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (2.0.10) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Browser Use, Chrome DevTools MCP, MCP Server Browser
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Lets AI do web tasks for you, such as filling forms, searching and extracting data, in the maker’s cloud browsers or on your computer.
Lets AI use Chrome’s developer tools to inspect pages, find what makes them slow and spot errors. Made by the Chrome DevTools team.
MCP server for browser use access
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
MCP server that turns your browser into a filesystem. AI agents use ls, cd, grep, find, click, and type to browse the web — the same way you'd navigate a Linux filesystem.
DOMShell maps Chrome's Accessibility Tree to a virtual filesystem. Every DOM element becomes a file or directory. Agents work with familiar commands instead of raw selectors and coordinates.
DOMShell supports three install paths — pick whichever fits your setup. Path 1 is the documented default and what 99% of users want; Paths 2 and 3 exist if you want lifecycle management across several MCP servers.
npm install -g @apireno/domshell
Or run directly without installing:
npx @apireno/domshell
Works on macOS, Linux, and Windows with Node 18+. Nothing else required.
Run DOMShell in a container — useful if you don't want a global Node install or you want process isolation. Requires Docker Desktop. The token is persisted to a gitignored .env file so it survives container restarts and host reboots:
git clone https://github.com/apireno/DOMShell && cd DOMShell/mcp-server
cp .env.example .env
docker compose build # produces domshell-mcp-server:latest docker compose up -d docker compose logs -f
The container maps ports 3001 (MCP HTTP) and 9876 (WebSocket bridge to the Chrome extension) to your loopback interface, so the Chrome extension reaches it exactly as it would the native install. restart: unless-stopped brings the container back automatically when Docker Desktop starts (toggle "Start Docker Desktop when you log in" in Docker Settings to make Path 2 fully reboot-resilient).
Use ToolHive (thv) to manage the container's lifecycle alongside any other MCP servers you're running. Same .env file Path 2 uses, just sourced by thv:
brew tap stacklok/tap && brew install thv # one-time
cd DOMShell/mcp-server cp .env.example .env # edit DOMSHELL_TOKEN if you haven't already docker compose build # produces domshell-mcp-server:latest
thv run \ --name domshell-mcp-server \ --transport streamable-http \ --target-port 3001 \ -p 9876:9876 \ --env-file .env \ domshell-mcp-server:latest
thv list # workload status (URL on the proxy port) thv logs domshell-mcp-server # tail logs
The container is reachable on http://127.0.0.1:3001/mcp because --target-port 3001 auto-publishes that port to host loopback — your existing MCP client config (Claude Desktop, Cursor, …) keeps working without changes.
Path 3 needs a one-time launchd agent for reboot autostart (Path 2 survives reboot through Docker Desktop alone). Full reboot table, launchd plist template, autostart script, and a simulated-reboot verification: docs/deploy/container-and-toolhive.md.
You also need the DOMShell Chrome Extension — the MCP server talks to the browser through it.
npx @apireno/domshell init
The setup wizard detects installed MCP clients (Claude Desktop, Cursor, Windsurf), generates a secure token, and writes the config. Use --yes for non-interactive mode.
Then:
connect (printed by the wizard)Add this to your Claude Desktop MCP settings (claude_desktop_config.json):
{
"mcpServers": { "domshell": { "command": "npx", "args": ["-y", "@apireno/domshell", "--allow-write"] } } }
For the stdio proxy (required if your client needs command/args format):
{
"mcpServers": { "domshell": { "command": "npx", "args": ["-y", "-p", "@apireno/domshell", "domshell-proxy", "--port", "3001", "--token", "YOUR_TOKEN"] } } }
We tested DOMShell against Computer-in-the-Cloud (CiC) — both using Claude as the underlying model — across 4 web tasks over 8 trials.
| Metric | DOMShell | CiC |
|---|---|---|
| Avg API calls per task | 4.3 | 8.6 |
| Hardest task (T4) | 6.0 calls | 13.0 calls |
| Cold start vs CiC warm cache | 4.5 calls | 5.5 calls |
DOMShell uses 2× fewer API calls to complete the same tasks. The filesystem metaphor gives the model a mental map of the page, so it spends less time exploring and more time extracting.
Full experiment data: experiments/claude_domshell_vs_cic
Default (recommended): the single `domshell_execute` tool. Pass any DOMShell command as a string — "ls", "cd tabs/123", "open https://example.com" — or pass several newline-separated for a whole workflow in one call. One tool, one approval, the full command vocabulary in the tool description.
Multi-line semantics: when command contains newlines, each line runs in order in the same MCP session and lane, so cwd, env, and history persist between lines. An error on one line does not halt the rest — its message is included in the combined output and subsequent lines still run. This is the right shape for cleanup-line idioms like "cd path\ngrep pattern\ncd back": the trailing restore runs even if the middle step errors. Implementation: mcp-server/index.ts:1115-1136.
Lanes & multi-agent. Every reply ends with [lane: ]. Multiple MCP clients can connect simultaneously, each in its own isolated Chrome tab group. To carve sub-lanes within a single client (e.g. two Claude Desktop chats), pass group_id: "new" on the first call and carry the returned id thereafter. See CHANGELOG.md.
--granularStart the server with --granular and the 38 per-command tools are exposed alongside domshell_execute. Use it when you want per-operation approval in the client UI.
Read tier (always available): ls, cd, pwd, cat, find, grep, tree, text, read, tabs, here, refresh, diff, eval, functions, watch, for, script, each, extract_links, extract_table
Write tier (`--allow-write`): click, focus, type, scroll, navigate, open, submit, back, forward, close, select, js, screenshot, wait, call
Sensitive tier (`--allow-sensitive`): whoami
| Flag | Description |
|---|---|
--allow-write | Enable write-tier tools (click, type, navigate, etc.) |
--allow-sensitive | Enable sensitive-tier tools (whoami) |
--allow-all | Enable all tiers |
--granular | Expose the 38 per-command tools alongside domshell_execute |
--port N | WebSocket port (default: 9876) |
--mcp-port N | HTTP MCP port (default: 3001) |
--domains a.com,b.com | Restrict to specific domains |
--token TOKEN | Set auth token (auto-generated if omitted) |
--log-file PATH | Audit log location (default: audit.log) |
--confirm | Opt in to per-action y/n prompts in the server terminal before each write. Off by default. |
--no-confirm | No-op (kept for backward compatibility — per-action prompts are off by default). |
Every command goes through a 4-tier security model:
--allow-write (navigate, open, back, forward)--allow-write (click, type, js, select)--allow-sensitive (whoami, cookie access)All commands are logged to an audit file. Domain allowlists restrict which sites the agent can access. Auth tokens protect the HTTP endpoint.
MCP Client (Claude, Cursor, etc.)
↓ HTTP :3001/mcp DOMShell MCP Server (Express + WebSocket) ↓ WebSocket :9876 DOMShell Chrome Extension (CDP 1.3) ↓ Chrome Debugger Protocol Browser DOM + Accessibility Tree
Built by Pireno.
MIT