agent-browser
agent-browser official site ↗Last checked against the official docs:
What it does
A browser automation CLI from Vercel Labs, built for AI agents. The agent drives a real browser one short shell command at a time: snapshot returns the page as compact text with a ref such as @e1 for each element, the agent clicks or fills a ref, then takes a new snapshot to check the result. The browser stays open between commands. It uses Chrome for Testing by default and can also attach to a Chrome you already have running. It ships version-matched skills for agents, and agent-browser mcp runs it as an MCP server over stdio. Native binaries for macOS, Linux and Windows. Apache-2.0 licensed.
Who it's for
People who want Claude Code, Codex, Cursor or another agent to open pages, fill forms, take screenshots and check their own web app, either through shell commands or as an MCP server.
How to set it up
Install the CLI globally, then download Chrome for Testing (first time only). On Linux, agent-browser install --with-deps also installs the browser's system libraries. Homebrew works too: brew install agent-browser.
bashnpm install -g agent-browser agent-browser installTry the basic loop from your terminal. Refs describe the page at the time of the snapshot, so take a new snapshot after the page changes:
bashagent-browser open example.com agent-browser snapshot -i agent-browser click @e1 agent-browser get url agent-browser closeTo let a coding agent use it through the shell, install the discovery skill. It tells the agent to load agent-browser skills get core, so the instructions always match your installed version:
bashnpx skills add vercel-labs/agent-browserOr add it to an MCP client. The default core tool profile keeps the tool list small; agent-browser mcp --tools all exposes every tool, and profiles can be combined, for example --tools core,network:
json{ "mcpServers": { "agent-browser": { "command": "agent-browser", "args": ["mcp"] } } }Web pages can contain text written to steer an agent. To limit what it can reach, set AGENT_BROWSER_ALLOWED_DOMAINS (for example "example.com,*.example.com"), and set AGENT_BROWSER_CONTENT_BOUNDARIES=1 to wrap page output in markers that separate it from tool output. If something stops working, agent-browser doctor checks the install, and agent-browser upgrade updates it.
Check the official agent-browser docs for the latest steps.
Install agent-browser in your client
Runs on your computer. Needs: The agent-browser CLI installed globally (npm install -g agent-browser), then agent-browser install for Chrome for Testing. Sign-in or keys: None.
One-click install
These buttons open the app on your computer (it needs to be installed already). The app asks you to confirm before it adds the server: review the command or URL it shows and check it matches the snippet below before you approve.
Claude Code
Run in a terminal
claude mcp add --transport stdio agent-browser -- agent-browser mcpEverything after -- is the server command. Run /mcp inside Claude Code to check it connected.
Claude Desktop
Settings → Developer → Edit Config (claude_desktop_config.json)
{
"mcpServers": {
"agent-browser": {
"command": "agent-browser",
"args": [
"mcp"
]
}
}
}Fully quit and reopen Claude Desktop after saving.
Cursor
.cursor/mcp.json in a project, or ~/.cursor/mcp.json for all projects
{
"mcpServers": {
"agent-browser": {
"command": "agent-browser",
"args": [
"mcp"
]
}
}
}VS Code
.vscode/mcp.json (note the top-level "servers" key)
{
"servers": {
"agent-browser": {
"type": "stdio",
"command": "agent-browser",
"args": [
"mcp"
]
}
}
}Codex
Run in a terminal, or edit ~/.codex/config.toml
CLI
codex mcp add agent-browser -- agent-browser mcpOr in ~/.codex/config.toml
[mcp_servers.agent-browser]
command = "agent-browser"
args = ["mcp"]- Add --tools all to the args for the full tool set, or a profile list such as --tools core,network,react.
- If the server shows as failed or disconnected, see fixing MCP error -32000.
- Compare every server's runtime and sign-in needs in the MCP server requirements table.
Checked against the official docs. Snippets use placeholders; keep real keys out of files you commit. Windsurf is not listed because we have not verified its format.
Set it up / Fixes
Step-by-step guides for getting agent-browser running and fixing common errors.
Example prompts
Use agent-browser to open http://localhost:3000, sign up with a test email, and tell me if the welcome page loads.Open our pricing page, take a full-page screenshot, and list any buttons that are covered or don't respond to a click.Check the browser console and network errors on the checkout page after adding an item to the cart.Made agent-browser? Add the badge
If you like, show that agent-browser is listed and hand-checked here. It's optional: listings are free and we never ask for a link back.
Get the Markdown or HTML
Markdown (for a GitHub README)
[](https://www.pluginstackai.com/plugins/agent-browser/)HTML (for a website)
<a href="https://www.pluginstackai.com/plugins/agent-browser/"><img src="https://www.pluginstackai.com/badge/hand-checked.svg" alt="Hand-checked on PluginStack" width="226" height="28"></a>Free: MCP Starter Checklist
After you set this tool up, use the one-page checklist so your next MCP server doesn't fail on first connect.
More MCP Servers
- Vercel Labs
agent-desktop
Computer use for AI agents from Vercel Labs: it lets an agent see and operate desktop apps on macOS, Windows and Linux through the operating system's accessibility tree instead of screenshots and pixel matching. snapshot returns an app's UI as JSON with a ref for each element, the agent clicks or types on a ref, then takes a new snapshot to check the result. There is no model inside; the loop runs in your agent. It ships as a CLI and a C library, and agent-desktop mcp serves every command as an MCP tool over stdio. Apache-2.0 licensed.
- Apify
Apify MCP Server
Apify's official MCP server. It lets an agent search Apify Store and run its ready-made scrapers and automation tools (called Actors) for websites, search engines, maps, social media and e-commerce, then read the results from your Apify datasets. By default it loads Actor search and run tools, Apify docs search, and the Web Search and Web Fetch Actors. The hosted server at mcp.apify.com signs you in with OAuth. MIT licensed; running Actors uses your Apify plan (a free plan includes $5 of monthly usage; most Store Actors charge per event).
- Brave
Brave Search MCP Server
Brave's official MCP server for the Brave Search API. It adds web, local, place, image, video and news search tools, plus LLM context and AI summarization. Version 2.x uses stdio by default, with HTTP as an option. MIT licensed.
- Google (Chrome DevTools)
Chrome DevTools MCP
Lets a coding agent control and inspect a live Chrome browser through Chrome DevTools (Google now calls it "Chrome DevTools for agents"; the package is chrome-devtools-mcp). It can record performance traces, read network requests and console messages (with source-mapped stack traces) and automate pages with Puppeteer. A CLI is included for use without MCP. Apache-2.0.
- Cloudflare
Cloudflare MCP Servers
Cloudflare's official remote MCP servers. The recommended Cloudflare API MCP server (https://mcp.cloudflare.com/mcp, maintained in the cloudflare/mcp repo) reaches the whole Cloudflare API through a few code-mode tools, and the repo also lists product servers for docs, containers, Browser Run and more. All are hosted by Cloudflare, so there is nothing to install. Apache-2.0.
- Upstash
Context7
Pulls up-to-date, version-specific library documentation and code examples into your prompt, so the AI stops relying on outdated training data or made-up APIs.