Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
作者提供的说明(英文原文)
Let your coding agents use your real, signed-in Chrome, in background tabs that never steal focus.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tabhand": {
"command": "npx",
"args": [
"-y",
"tabhand",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add tabhand -- npx -y tabhand mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tabhand": {
"command": "npx",
"args": [
"-y",
"tabhand",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tabhand": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tabhand",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过域名 tabhand.dev 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.10.1)于15天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Browser Use, Chrome DevTools MCP, MCP Server Browser
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
MCP server for Chrome DevTools
MCP server for browser use access
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Tabhand
Let your AI agents use your own Chrome, signed in to your accounts,
in background tabs that never steal your focus.
tabhand.dev · Docs · Chrome Web Store
https://github.com/user-attachments/assets/d5fe5c5a-c012-471f-bf3b-10fa754c382d
Video not playing? Watch it on tabhand.dev
npx tabhand setup
Works with Claude Code, Codex, Cursor, OpenCode, Gemini CLI, Copilot and more: 19 agents in all, plus anything else that speaks MCP.
Then add the extension from the Chrome Web Store. Setup opens the page for you. It works in Brave, Edge and Dia too.
agent ──stdio──▶ tabhand mcp ──Unix socket──▶ native host ──native messaging──▶ extension ──chrome.debugger──▶ agent's tabs
active: false, inside a tab group named after the agent. Focus emulation keeps those tabs rendering, so clicks, typing and screenshots work without bringing anything to the front. Agent tabs are muted, and the agent moves on once a page is usable instead of waiting for every video to load.tabhand cursor --name Acme --color '#FF5A1F' --icon initial.npx tabhand setup
That's all:
~/.tabhand and connects it to Chrome, and to Brave, Edge and Dia (macOS) if you have them.mcp add command, setup uses it. Otherwise it edits the agent's settings file in place, keeping comments, and backs up the original to ~/.tabhand/backups.Agents it knows:
To add it to only some of them, run npx tabhand setup --harness claude,codex.
Using Brave, Edge or Dia? Add the extension there from the same Chrome Web Store page. Edge asks you to allow extensions from other stores first. Each browser shows up to agents as one more profile: click the Tabhand icon in it and give it a name, such as "Brave", so agents can ask for it. Arc isn't supported: tab groups and screenshots never finish there, so Tabhand stays out of Arc even if you add the extension. Arc shuts down on December 22, 2026; Dia works.
tabhand status checks the install, the Chrome connection and each agent. tabhand remove undoes it all. Run npx tabhand@latest setup again to update.
Any other MCP client can run ~/.tabhand/bin/tabhand mcp itself (on Windows, %USERPROFILE%\.tabhand\bin\tabhand.cmd mcp).
winget install OpenJS.NodeJS.LTS.npx says running scripts is disabled on this system, run npx.cmd tabhand setup instead, or use Command Prompt.HKEY_CURRENT_USER in the registry. Nothing needs an administrator.npm install
node bin/tabhand.mjs setup # builds dist/tabhand.mjs and installs it from this checkout node bin/tabhand.mjs reload # after changing the extension's code
From a checkout, setup has you load the extension unpacked (Developer mode, then "Load unpacked") instead of adding it from the Chrome Web Store.
Setup copies a single bundled file (dist/tabhand.mjs, built by npm run build), because macOS doesn't let Chrome's child processes read Documents, Desktop or Downloads. Agents and Chrome both start it through ~/.tabhand/bin/tabhand. That launcher remembers which Node.js ran setup, since agent apps don't get your shell's PATH. If that Node.js is removed later, it finds another one. If Chrome never connects, the bridge's log at ~/Library/Application Support/tabhand/host.log says why.
On Windows, Chrome starts the bridge through ~\.tabhand\bin\tabhand-host.cmd, which the registry points it to, and agents run the Node.js that ran setup with ~\.tabhand\app\tabhand.mjs directly, since they start programs without a shell. The log is in %LOCALAPPDATA%\tabhand\host.log, and anything the bridge printed while failing to start is in host-errors.log next to it.
Windows-only code lives in src/windows.mjs and extension/windows.js. The shared files call into them only behind a Windows check, and keep their macOS code as it is.
| Tool | What it does |
|---|---|
browser_open_tab | Open a background tab in the agent's tab group, optionally loading a URL, in the Chrome profile it asks for |
browser_navigate | Load a URL in one of the session's tabs |
browser_snapshot | Read the page as an accessibility outline; actionable elements, including ones a page made clickable or draggable out of plain elements, get refs like e123 |
browser_click | Click an element by ref, or by the text it shows |
browser_hover | Move the pointer over an element (by ref or text) to reveal controls that only show on hover, and get a fresh snapshot with refs for them |
browser_drag | Drag one element onto another, by ref or text: reorder lists, move cards between columns. Works with the browser's own drag and drop and with pages that follow the mouse |
browser_type | Type into a field, optionally clearing it first and pressing Enter after, or choose a dropdown option by its text |
browser_press_key | Press a key or combination such as Shift+Tab |
browser_scroll | Scroll up or down |
browser_upload_file | Attach files from your computer to a file field, or through the button that opens a file picker (no system dialog appears) |
browser_handle_dialog | Accept or dismiss a confirm or prompt dialog the page opened (alerts are closed for you) |
browser_screenshot | Screenshot a tab, even in the background |
browser_list_tabs | List the session's tabs, in every Chrome profile |
browser_list_profiles | List the Chrome profiles that have Tabhand, by name, and whether each is on or paused |
browser_close_tab | Close one of the session's tabs |
npm test runs all of these except the smoke test.node test/setup.mjs runs setup, status and remove in a throwaway home folder holding existing agent configs. It checks that Tabhand gets added, that comments and other settings survive, that a second run changes nothing, and that the launcher serves the MCP server.node test/setup-windows.mjs does the same on Windows, with th只显示了开头部分;其余内容请在仓库中阅读