Ad space · Your tool here
PluginStack
MCP Servers · by Vercel Labs

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

  1. 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.

    bash
    npm install -g agent-browser
    agent-browser install
  2. Try 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:

    bash
    agent-browser open example.com
    agent-browser snapshot -i
    agent-browser click @e1
    agent-browser get url
    agent-browser close
  3. To 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:

    bash
    npx skills add vercel-labs/agent-browser
  4. Or 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"]
        }
      }
    }
  5. 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

bash
claude mcp add --transport stdio agent-browser -- agent-browser mcp

Everything after -- is the server command. Run /mcp inside Claude Code to check it connected.

Claude Desktop

Settings → Developer → Edit Config (claude_desktop_config.json)

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

json
{
  "mcpServers": {
    "agent-browser": {
      "command": "agent-browser",
      "args": [
        "mcp"
      ]
    }
  }
}
VS Code

.vscode/mcp.json (note the top-level "servers" key)

json
{
  "servers": {
    "agent-browser": {
      "type": "stdio",
      "command": "agent-browser",
      "args": [
        "mcp"
      ]
    }
  }
}
Codex

Run in a terminal, or edit ~/.codex/config.toml

CLI

bash
codex mcp add agent-browser -- agent-browser mcp

Or in ~/.codex/config.toml

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

prompt
Use agent-browser to open http://localhost:3000, sign up with a test email, and tell me if the welcome page loads.
prompt
Open our pricing page, take a full-page screenshot, and list any buttons that are covered or don't respond to a click.
prompt
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.

Hand-checked on PluginStack
Get the Markdown or HTML

Markdown (for a GitHub README)

markdown
[![Hand-checked on PluginStack](https://www.pluginstackai.com/badge/hand-checked.svg)](https://www.pluginstackai.com/plugins/agent-browser/)

HTML (for a website)

html
<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>

About the badge

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.

Markdown download + occasional PluginStack updates. No spam. Privacy policy.

See all MCP Servers on PluginStack