BrowserDo

BrowserDo

Built for AI agents. Shared with people.

Embiody is a Windows browser your AI agent works in, in the background andat full speed, while you keep using your PC and can step in at any time. BrowserDo is theMCP server that connects your agent to it. Add it to ClaudeCode, Claude Desktop, Codex, Cursor, VS Code or Gemini CLI, and your agent can browse, click, typeand read pages, including sites you are signed in to.

Why BrowserDo

1. Works in the background at full speed, and leaves your screen to you

Pages run at full speed in background tabs, background windows, minimized windows and hiddenwindows. Your agent does not need the browser in front of you, so you keep using your computerwhile it works, and it can work in a dozen tabs at once.

Ordinary Chrome slows down pages you are not looking at. In our test, a browser window wascompletely covered by another window for 7 minutes:

No launch flags are needed for this. One limit: a page opened while its window is minimizedmay come back without a screenshot; its text and element numbers are still there.

2. Works where bots get blocked — because it isn't one

Your agent works in your own browser, on your behalf, so sites with anti-bot protection treat itthe way they treat you.

3. Sees the whole page and clicks the right thing

• Content inside embedded frames from other sites, such as payment forms and sign-in boxes, canbe read and clicked.
• Elements covered by a popup or overlay get no number, so the agent can't click something youcan't see.
• Long pages are read whole, not only the part on screen.
• An element off screen is scrolled into view before it is clicked.
• Clicks land where they should across multiple monitors and at any display scaling.
• Every element number belongs to one snapshot. A number from an older snapshot is refusedbefore anything is clicked, instead of hitting whatever took its place.

4. You can see what the agent is doing

A tab the agent is working in shows a virtual mouse pointer, a frame around the page and amarker on the tab. Open it any time to watch.

5. You and the agent share one browser without getting in each other's way

If you click or type in a tab the agent is working in, you are asked whether to take it over.The agent asks before it touches a tab of yours.

6. Several steps in one call

browser_batch runs several actions (clicks, typing, key presses) in a row and returns a freshsnapshot of the page, so the agent needs fewer round trips and fewer tokens.

7. Reads the page itself, not a summary

browser_read_pages returns the page's own text, links included, from pages built by scripts andfrom sites you are signed in to. It can stand in for Claude Code's WebFetch, which returns a shortmodel-written summary. In our comparison of 8 pages, BrowserDo read a BBC News article thatWebFetch could not fetch, and read all 8 pages in parallel in about 20 seconds.

8. Sees the browser's own popups

Permission bubbles, menus, Save As dialogs, "Leave site?" prompts and alerts are reported in everysnapshot, with the ways each one can be answered.

9. Current engine, signed releases

Built on Chromium 156. Releases are signed, and the browser updates itself, checking thesignature of every update.

Requirements

• Windows 10 or 11, 64-bit (Embiody is Windows only for now)
• Node.js 20 or newer. Check with node -v. Without it, BrowserDo fails to start (Claude Code shows"Failed to connect"). Install it with winget install OpenJS.NodeJS.LTS, then restart your client.
• The Embiody browser, version 0.9.0.3 or newer: installed automatically the first time BrowserDostarts. That is a download of about 140 MB and takes a few minutes; your client can use BrowserDoat once, and until the browser is ready each tool replies with the progress. With an older one, BrowserDo opens the browser's update page and asks you to restartthe browser and BrowserDo once it has updated (details).

No API key is needed. Your agent drives the browser with its own model.

Install

BrowserDo runs as npx -y browserdo-mcp. Pick your client and follow only that section; the othersare for other clients.

Claude Code

claude mcp add browserdo -- npx -y browserdo-mcp

Add --scope project to share it with your team through .mcp.json, or --scope user to use itin every project.

Claude Desktop

Edit %APPDATA%\Claude\claude_desktop_config.json:

{
  "mcpServers": {
    "browserdo": {
      "command": "npx",
      "args": ["-y", "browserdo-mcp"]
    }
  }
}

Codex

codex mcp add browserdo -- npx -y browserdo-mcp

Or add to ~/.codex/config.toml:

[mcp_servers.browserdo]
command = "npx"
args = ["-y", "browserdo-mcp"]

Cursor

Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (one project):

{
  "mcpServers": {
    "browserdo": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "browserdo-mcp"]
    }
  }
}

VS Code

Run MCP: Add Server from the Command Palette, choose Command (stdio) and enternpx -y browserdo-mcp. Or add to .vscode/mcp.json:

{
  "servers": {
    "browserdo": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "browserdo-mcp"]
    }
  }
}

Gemini CLI

Add to ~/.gemini/settings.json (all projects) or .gemini/settings.json (one project):

{
  "mcpServers": {
    "browserdo": {
      "command": "npx",
      "args": ["-y", "browserdo-mcp"]
    }
  }
}

Other MCP clients

Add a local (stdio) MCP server in your client's settings, with command npx and arguments-y browserdo-mcp. Most clients take it in this shape:

{
  "mcpServers": {
    "browserdo": {
      "command": "npx",
      "args": ["-y", "browserdo-mcp"]
    }
  }
}

Then ask your agent to do something on the web:

Find me a direct flight from Sydney to Melbourne next Wednesday morning and show me thethree cheapest options.

Tools

Each tool is one browser action. windowId and tabId are optional everywhere; leave them outand the frontmost window and tab are used.

Settings

Set these in the env block of your client's config, or put them in a config file (copybrowserdo.config.example.yaml to browserdo.config.yaml next to where the server runs, or pass--config <path>). Environment variables win over the config file.

The example config file explains the rest: fallback models, timeouts, how long to let pagessettle. --transport sse serves MCP over HTTP at http://127.0.0.1:3000/sse instead of stdio; itanswers this machine only.

Privacy

BrowserDo has no telemetry, usage statistics or error reporting.

• Downloads: the first time it starts without Embiody installed, it downloads the installerfrom GitHub, or from a mirror if GitHub can't be reached.
• Updates: when your client starts BrowserDo with npx, npm checks the npm registry for thelatest version when it starts BrowserDo. That request is made by npm, not by BrowserDo.
• Your model: only browser_run_task sends anything to a model, and only to the endpoint youconfigure. The browser tools return pages to your own agent.
• On your computer: a debug log at %LOCALAPPDATA%\Embiody\BrowserDo\logs records the URLsvisited and the steps taken, never page content or your task. It keeps at most three 5 MB files.Snapshots are not saved unless you set EMBIODY_SAVE_SNAPSHOTS=1.
• Your profile: the agent works in your own Embiody, in its Default profile, so it can usethe sites you are signed in to there. Other Embiody profiles are not used, and neither are otherbrowsers on your computer, such as Chrome or Edge. To keep the agentapart, set EMBIODY_USER_DATA_DIR to a folder of its own.

See the privacy policy and theEmbiody end-user license agreement.

Optional: browser_run_task

If you would rather hand over a whole task than drive the browser step by step,browser_run_task runs it inside BrowserDo with a vision model of your choice (anyOpenAI-compatible endpoint), and keeps the screenshots out of your agent's context.

"env": {
  "EMBIODY_VLLM_ENDPOINT": "<your-openai-compatible-endpoint>",
  "EMBIODY_VLLM_MODEL": "<your-vision-model>",
  "EMBIODY_VLLM_API_KEY": "<your-api-key>"
}

When the task needs you, it asks. A step only you can do, like a password or a code sent to you,hands you the tab first and continues once you say you're done. In clients that supportquestions during a task (tasks.requests.elicitation.create, as in Claude Code), the questionappears in your conversation; elsewhere the task ends with the question, and you answer by callingit again with humanReply.

browser_stop_task stops a running task at the end of its current step.

Keep your API key out of files that get committed. If your client can expand environmentvariables in its config, use that; otherwise keep the key in a config file outside the repositoryand point at it with --config.

Notes

• Claude Code keeps old tool definitions in a conversation. After BrowserDo is upgraded, starta new conversation to see new tools and parameters.
• BrowserDo speaks MCP protocol version 2025-11-25 and negotiates down to older versions.

Development

npm install
npm run build
npm test          # 897 tests
npm run test:fast # unit and module tests only

See test/README.md for the test layout.

License

BrowserDo is licensed under the Apache License, Version 2.0; see LICENSE. The Embiodybrowser it installs is covered by the Embiody EULA.