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)
MCP server with WebdriverIO for browser and mobile app automation (iOS/Android via Appium)
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": {
"webdriverio": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp"
]
}
}
}在终端中运行这条命令
claude mcp add webdriverio -- npx -y @wdio/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"webdriverio": {
"command": "npx",
"args": [
"-y",
"@wdio/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": {
"webdriverio": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wdio/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6日
注册名称已通过 GitHub 账户 webdriverio 验证,该账户拥有此仓库
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(4.1.0)于7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。
A Model Context Protocol (MCP) server that enables AI assistants to interact with web browsers, local Electron applications, and mobile applications using WebdriverIO. Automate Chrome, Firefox, Edge, Safari, Electron, iOS, and Android through a unified interface.
Add the following configuration to your MCP client settings:
Standard config (works in most clients):
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS), %APPDATA%\Claude\claude_desktop_config.json (Windows), or ~/.config/Claude/claude_desktop_config.json (Linux):
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
Claude Code
claude mcp add wdio-mcp -- npx -y @wdio/mcp@latest
Cline
Add to your VS Code settings.json or cline_mcp_settings.json file:
{
"mcpServers": { "wdio-mcp": { "type": "stdio", "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
Cursor
Go to Cursor Settings → MCP → Add new MCP Server, or create .cursor/mcp.json:
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
Codex
Use the Codex CLI:
codex mcp add wdio-mcp npx "@wdio/mcp@latest"
Or edit ~/.codex/config.toml:
[mcp_servers.wdio-mcp]
command = "npx" args = ["@wdio/mcp@latest"]
Goose
Go to Advanced settings → Extensions → Add custom extension, or run:
goose configure
Or edit ~/.config/goose/config.yaml:
extensions:
wdio-mcp: name: WebDriverIO MCP cmd: npx args: [ -y, "@wdio/mcp@latest" ] enabled: true type: stdio
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
Zed
Edit Zed settings (~/.config/zed/settings.json):
{
"context_servers": { "wdio-mcp": { "source": "custom", "command": "npx", "args": [ "-y", "@wdio/mcp@latest" ] } } }
VS Code (Copilot)
code --add-mcp '{"name":"wdio-mcp","command":"npx","args":["-y","@wdio/mcp@latest"]}'
⚠️ Restart Required: After adding the configuration, fully restart your MCP client to apply the changes.
If you prefer to install globally:
npm install -g @wdio/mcp
Then use wdio-mcp as the command:
{
"mcpServers": { "wdio-mcp": { "command": "wdio-mcp" } } }
📖 Need help? Follow the MCP install guide.
By default the server uses stdio (subprocess) transport. For clients that cannot launch subprocesses (e.g. llama.cpp, OpenAI Codex secure mode), enable HTTP transport:
npx @wdio/mcp --http --port 3000
| Flag | Default | Description |
|---|---|---|
--http | — | Enable HTTP transport mode |
--port | 3000 | Port to listen on |
--allowedHosts | localhost,127.0.0.1,::1 | Allowed Host header values (DNS rebinding protection) |
--allowedOrigins | _(none — browser clients blocked)_ | Allowed Origin values for CORS. Use * to allow all. |
Then point your MCP client at http://localhost:3000/mcp.
npm install -g appiumappium driver install xcuitest (requires Xcode on macOS)appium driver install uiautomator2 (requires Android Studio)Start the Appium server before using mobile features:
appium
Run browser and mobile app tests on cloud real devices and browsers without any local setup. Currently supports BrowserStack, Sauce Labs, LambdaTest, TestingBot, and Digital.ai Testing.
Set your provider credentials as environment variables or in your MCP client config:
BrowserStack
export BROWSERSTACK_USERNAME=your_username
export BROWSERSTACK_ACCESS_KEY=your_access_key
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": ["-y", "@wdio/mcp@latest"], "env": { "BROWSERSTACK_USERNAME": "your_username", "BROWSERSTACK_ACCESS_KEY": "your_access_key" } } } }
Sauce Labs
export SAUCE_USERNAME=your_username
export SAUCE_ACCESS_KEY=your_access_key
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": ["-y", "@wdio/mcp@latest"], "env": { "SAUCE_USERNAME": "your_username", "SAUCE_ACCESS_KEY": "your_access_key" } } } }
| SAUCE_USERNAME | Sauce Labs username (required) | | SAUCE_ACCESS_KEY | Sauce Labs access key (required) |
The data center is set per-session via the region parameter in start_session (defaults to eu-central-1).
LambdaTest (TestMu)
export TESTMU_USERNAME=your_username
export TESTMU_ACCESS_KEY=your_access_key
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": ["-y", "@wdio/mcp@latest"], "env": { "TESTMU_USERNAME": "your_username", "TESTMU_ACCESS_KEY": "your_access_key" } } } }
| TESTMU_USERNAME | LambdaTest username (required) | | TESTMU_ACCESS_KEY | LambdaTest access key (required) |
TestingBot
export TESTINGBOT_KEY=your_key
export TESTINGBOT_SECRET=your_secret
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": ["-y", "@wdio/mcp@latest"], "env": { "TESTINGBOT_KEY": "your_key", "TESTINGBOT_SECRET": "your_secret" } } } }
| TESTINGBOT_KEY | TestingBot key (required) | | TESTINGBOT_SECRET | TestingBot secret (required) |
Digital.ai Testing
export DIGITALAI_CLOUD_URL=https://your-cloud.example.com
export DIGITALAI_ACCESS_KEY=your_access_key
{
"mcpServers": { "wdio-mcp": { "command": "npx", "args": ["-y", "@wdio/mcp@latest"], "env": { "DIGITALAI_CLOUD_URL": "https://your-cloud.example.com", "DIGITALAI_ACCESS_KEY": "your_access_key" } } } }
| DIGITALAI_CLOUD_URL | Digital.ai cloud host, e.g. https://your-cloud.example.com (required) | | DIGITALAI_ACCESS_KEY | Digital.ai access key (required) |
The access key is sent via the digitalai:options capability (mobile) or the flat digitalai:accessKey capability (web).
Report pass/fail status: WebdriverIO defaults to the BiDi protocol, over which Digital.ai's cloud cannot observe command failures — so reports default to "Passed". To make the cloud reflect actual pass/fail, opt in to classic WebDriver per session:
start_session({
provider: 'digitalai', platform: 'browser', browser: 'chrome', os: 'Windows 10', capabilities: { 'wdio:enforceWebDriverClassic': true } })
(Pure client-side assertion failures still report as "Passed" — only failures that reach the cloud as WebDriver command errors are detected.)
Mobile (Appium): configure your Digital.ai project for Appium-server execution and pick its default Appium version via the project's "Manage default Appium server version" setting — the version is chosen at the project level (and tracks the versions your cloud supports), so this MCP does not pin one. See Appium Server Test Execution.
Run a browser on a specific OS/version combination:
// BrowserStack
start_session({ provider: 'browserstack', platform: 'browser', browser: 'chrome', // chrome | firefox | edge | safari browserVersion: 'latest', // default: latest os: 'Windows', // e.g. "Windows", "OS X" osVersion: '11', // e.g. "11", "Sequoia" reporting: { project: 'My Project', build: 'v1.2.0', session: 'Login flow' } })
// Sauce Labs start_session({ provider: 'saucelabs', platform: 'browser', browser: 'chrome', os: 'Windows', // combined with osVersion → platformName osVersion: '11', // e.g. "11", "15" (numbered Mac naming) region: 'eu-central-1', // default: eu-central-1 reporting: { build: 'v1.2.0', session: 'Login flow' } })
// LambdaTest start_session({ provider: 'testmu', platform: 'browser', browser: 'chrome', os: 'Windows', // combined with osVersion → platformName osVersion: '11', // e.g. "11", "Sequoia" (optional) reporting: { project: 'My Project', build: 'v1.2.0', session: 'Login flo
只显示了开头部分;其余内容请在仓库中阅读