AI 어시스턴트가 웹 브라우저, 로컬 Electron 애플리케이션, iOS 및 Android 모바일 앱을 자동화할 수 있도록 지원합니다.
다른 이름 webdriverio/mcp, @wdio/mcp
- 스타
- 44
- Tools
- 17
- 다운로드, 30일
- —
- 최신 버전
- 4.1.0
- 마지막 커밋
- 2026년 11월 15일
- 라이선스
- MIT
WebDriverIO MCP란?
AI 어시스턴트가 웹 브라우저, 로컬 Electron 애플리케이션, iOS 및 Android 모바일 앱을 자동화할 수 있도록 지원합니다. 17개 도구를 제공합니다. 예: start_session, close_session, navigate.
프로젝트 README에서 생성된 요약
WebDriverIO MCP server 정보
이 MCP server를 통해 웹 브라우저, 모바일 애플리케이션, 로컬 Electron 앱을 자동화할 수 있습니다. AI 어시스턴트가 Chrome, Firefox, Edge, Safari뿐만 아니라 iOS 및 Android 기기와 상호작용할 수 있는 통합 인터페이스를 제공합니다. 개발자는 이를 사용하여 로컬 환경에서 테스트를 실행하거나 BrowserStack, Sauce Labs, LambdaTest, TestingBot, Digital.ai Testing과 같은 클라우드 제공업체에 연결할 수 있습니다.
이 server를 사용하려면 npx 또는 글로벌 npm 패키지로 설치할 수 있습니다. 서브프로세스 클라이언트를 위해 주로 stdio transport를 사용하지만, 서브프로세스를 실행할 수 없는 클라이언트를 위해 지정된 포트에서의 HTTP transport도 지원합니다. 모바일 자동화를 위해서는 로컬 Appium server와 iOS용 xcuitest 또는 Android용 uiautomator2와 같은 특정 플랫폼 드라이버가 필요합니다. 클라우드 기반 테스트의 경우 환경 변수나 클라이언트 설정을 통해 사용자 이름 및 액세스 키와 같은 자격 증명을 제공해야 합니다.
활용 사례
- 1웹 브라우저 테스트 자동화AI에게 Chrome 또는 Safari와 같은 다양한 웹 브라우저에서 작업을 수행하도록 지시합니다.
- 2모바일 애플리케이션 테스트AI에게 iOS 시뮬레이터 또는 Android 에뮬레이터에서 자동화된 워크플로우를 실행하도록 지시합니다.
- 3클라우드에서 테스트 실행클라우드 서비스를 사용하여 원격 실제 기기에서 자동화된 브라우저 및 모바일 세션을 실행합니다.
- 4로컬 데스크톱 앱과 상호작용AI 어시스턴트를 사용하여 로컬 Electron 기반 소프트웨어 애플리케이션을 제어합니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
WebDriverIO MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 WebDriverIO MCP 설치
$ claude mcp add mcp -- npx -y @wdio/mcpCursor에 WebDriverIO MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp"
]
}
}
}VS Code에 WebDriverIO MCP 설치
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@wdio/mcp"
]
}
}
}VS Code CLI에 WebDriverIO MCP 설치
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@wdio/mcp"]}'Claude Desktop에 WebDriverIO MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp"
]
}
}
}Codex에 WebDriverIO MCP 설치
$ codex mcp add mcp -- npx -y @wdio/mcpCodex config.toml에 WebDriverIO MCP 설치
~/.codex/config.toml
[mcp_servers.mcp] command = "npx" args = ["-y", "@wdio/mcp"]
Gemini CLI에 WebDriverIO MCP 설치
$ gemini mcp add -s user mcp npx -- -y @wdio/mcpGemini settings.json에 WebDriverIO MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp"
]
}
}
}HostedMCP가 2026년 11월 16일에 실행 확인
@wdio/mcp 4.1.0을(를) 네트워크와 키가 없는 격리된 컨테이너에서 이 명령으로 실행했습니다. 응답하며 도구 17개를 보여 주었습니다.
WebDriverIO MCP 도구 17
tools/list로 서버에서 직접 읽음start_sessionStarts a browser, Electron app or mobile app session (closes the active one unless onExisting: "keep"). Browsers run headless at 1280x800 by default; pass navigationUrl to open a page right away. attach: true connects to a running Chrome via CDP.
close_sessionCloses the session, or with detach: true disconnects and leaves it running. Attached sessions and Appium sessions with noReset are detached unless detach: false.
navigateLoads a URL in the current tab and waits for the page load event. Resets page state — DOM, JS runtime, timers, and frame context are destroyed. Use instead of clicking links when the target URL is known.
switch_tabSwitches to a tab by handle or 0-based index (see get_tabs). Later tools act on that tab.
switch_frameSwitches into an iframe (ref or selector), or back to the top page when selector is omitted. Later tools act inside the frame until you switch back. Returns the frame's elements.
scrollScrolls the page vertically by a pixel amount. Browser-only — for mobile scrolling use swipe. Only supports up/down; no horizontal scrolling.
click_elementClicks an element. On web pages the result lists what changed (new elements with refs, or the new page). In apps it does not: take a snapshot to see the new screen. Several steps in a row: perform_actions.
set_valueReplaces the text of an input or textarea. On web pages the result lists what changed (new elements with refs, or the new page). In apps it does not: take a snapshot to see the new screen. To fill several fields or fill and then click, use one perform_actions call.
select_optionSelects an option of a <select> by its text. The result lists what changed on the page. Several steps in a row: perform_actions.
press_keyPresses a key or combination in the focused element, e.g. Enter, Tab, Escape, Control+a. The result lists what changed on the page. Several steps in a row: perform_actions.
perform_actionsRuns several actions in one call, e.g. fill a form and submit it, on the page or app screen, and returns what each one changed on web pages. Steps the current session does not support are rejected before any step runs. Stops at the first failure, when a step loads a new page, or before a key press that follows a click, select, check or uncheck that changed the page (continue with the new refs). value is the text for fill, the option for select and the keys for press.
snapshot읽기 전용The page or app screen as an accessibility tree with refs, e.g. `button "Save" [ref=e3]`. Pass refs to perform_actions for several steps, or to click_element/set_value/select_option for one. Default: interactive elements only, plain text is dropped; full: true shows it. find returns only the parts of the page that contain the text (with their refs); full: true includes all text; viewport: true limits it to what is on screen (not together with find).
| start_session | Starts a browser, Electron app or mobile app session (closes the active one unless onExisting: "keep"). Browsers run headless at 1280x800 by default; pass navigationUrl to open a page right away. attach: true connects to a running Chrome via CDP. | |
| close_session | Closes the session, or with detach: true disconnects and leaves it running. Attached sessions and Appium sessions with noReset are detached unless detach: false. | |
| navigate | Loads a URL in the current tab and waits for the page load event. Resets page state — DOM, JS runtime, timers, and frame context are destroyed. Use instead of clicking links when the target URL is known. | |
| switch_tab | Switches to a tab by handle or 0-based index (see get_tabs). Later tools act on that tab. | |
| switch_frame | Switches into an iframe (ref or selector), or back to the top page when selector is omitted. Later tools act inside the frame until you switch back. Returns the frame's elements. | |
| scroll | Scrolls the page vertically by a pixel amount. Browser-only — for mobile scrolling use swipe. Only supports up/down; no horizontal scrolling. | |
| click_element | Clicks an element. On web pages the result lists what changed (new elements with refs, or the new page). In apps it does not: take a snapshot to see the new screen. Several steps in a row: perform_actions. | |
| set_value | Replaces the text of an input or textarea. On web pages the result lists what changed (new elements with refs, or the new page). In apps it does not: take a snapshot to see the new screen. To fill several fields or fill and then click, use one perform_actions call. | |
| select_option | Selects an option of a <select> by its text. The result lists what changed on the page. Several steps in a row: perform_actions. | |
| press_key | Presses a key or combination in the focused element, e.g. Enter, Tab, Escape, Control+a. The result lists what changed on the page. Several steps in a row: perform_actions. | |
| perform_actions | Runs several actions in one call, e.g. fill a form and submit it, on the page or app screen, and returns what each one changed on web pages. Steps the current session does not support are rejected before any step runs. Stops at the first failure, when a step loads a new page, or before a key press that follows a click, select, check or uncheck that changed the page (continue with the new refs). value is the text for fill, the option for select and the keys for press. | |
| snapshot | The page or app screen as an accessibility tree with refs, e.g. `button "Save" [ref=e3]`. Pass refs to perform_actions for several steps, or to click_element/set_value/select_option for one. Default: interactive elements only, plain text is dropped; full: true shows it. find returns only the parts of the page that contain the text (with their refs); full: true includes all text; viewport: true limits it to what is on screen (not together with find). | 읽기 전용 |
도구 17개 모두 보기도구 수 줄이기
execute_scriptRuns JavaScript in the page (`return` a value; string args that match a selector are passed as elements) or, on Appium, a "mobile: <command>" with args. Prefer the dedicated tools for clicks and typing.
query_docs읽기 전용Search the official WebdriverIO documentation and return the most relevant excerpts with page, section and source URL. Use before answering any question about WebdriverIO APIs, configuration, services, reporters, selectors, or debugging. Query with 2-3 distinctive keywords, never a sentence: "appium setup", "devtools trace.zip" and "allure reporter" each return the right page first, while "how do I wire up appium in my config file" does not. A word can also collide with an unrelated page — `wire` matches Wire Protocol — so if a query misses, retry with the exact page title, which beats any paraphrase. Set fullPage for the whole page. To browse instead, read wdio://docs/index for every page title and its slug, then wdio://docs/page/{slug} for one page in full. Cite the `path` of any page you rely on.
get_screenshot읽기 전용Takes a screenshot of the current page or screen and returns a base64-encoded image, resized and compressed for model context limits.
get_tabs읽기 전용Lists all browser tabs with handle, title, URL, and which is active. Use before switch_tab to find the target handle or index. Browser-only.
enable_tools읽기 전용Adds more tools: mocks (mock network requests or Electron APIs); cookies (read, set and delete cookies); device (emulate a phone or tablet, fake the location); extensions (install and open a browser extension); attach (launch Chrome with remote debugging, attach to a running WebDriver or Appium session); elements (raw element list with bounds); cloud-apps (upload and list mobile apps on BrowserStack, Sauce Labs, TestMu, TestingBot, Digital.ai).
| execute_script | Runs JavaScript in the page (`return` a value; string args that match a selector are passed as elements) or, on Appium, a "mobile: <command>" with args. Prefer the dedicated tools for clicks and typing. | |
| query_docs | Search the official WebdriverIO documentation and return the most relevant excerpts with page, section and source URL. Use before answering any question about WebdriverIO APIs, configuration, services, reporters, selectors, or debugging. Query with 2-3 distinctive keywords, never a sentence: "appium setup", "devtools trace.zip" and "allure reporter" each return the right page first, while "how do I wire up appium in my config file" does not. A word can also collide with an unrelated page — `wire` matches Wire Protocol — so if a query misses, retry with the exact page title, which beats any paraphrase. Set fullPage for the whole page. To browse instead, read wdio://docs/index for every page title and its slug, then wdio://docs/page/{slug} for one page in full. Cite the `path` of any page you rely on. | 읽기 전용 |
| get_screenshot | Takes a screenshot of the current page or screen and returns a base64-encoded image, resized and compressed for model context limits. | 읽기 전용 |
| get_tabs | Lists all browser tabs with handle, title, URL, and which is active. Use before switch_tab to find the target handle or index. Browser-only. | 읽기 전용 |
| enable_tools | Adds more tools: mocks (mock network requests or Electron APIs); cookies (read, set and delete cookies); device (emulate a phone or tablet, fake the location); extensions (install and open a browser extension); attach (launch Chrome with remote debugging, attach to a running WebDriver or Appium session); elements (raw element list with bounds); cloud-apps (upload and list mobile apps on BrowserStack, Sauce Labs, TestMu, TestingBot, Digital.ai). | 읽기 전용 |
구성
BROWSERSTACK_ACCESS_KEYBROWSERSTACK_USERNAMEDIGITALAI_ACCESS_KEYDIGITALAI_CLOUD_URLSAUCE_ACCESS_KEYSAUCE_USERNAMETESTINGBOT_KEYTESTINGBOT_SECRETTESTMU_ACCESS_KEYTESTMU_USERNAME
| 이름 | 설명 | 유형 |
|---|---|---|
| BROWSERSTACK_ACCESS_KEY | — | |
| BROWSERSTACK_USERNAME | — | |
| DIGITALAI_ACCESS_KEY | — | |
| DIGITALAI_CLOUD_URL | — | |
| SAUCE_ACCESS_KEY | — | |
| SAUCE_USERNAME | — | |
| TESTINGBOT_KEY | — | |
| TESTINGBOT_SECRET | — | |
| TESTMU_ACCESS_KEY | — | |
| TESTMU_USERNAME | — |
자동 검사
2026년 11월 16일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능webdriverio/mcp is public and reachablegithub.com/webdriverio/mcp ↗통과
- 패키지가 이 저장소를 소스로 명시@wdio/mcp names webdriverio/mcp as sourcenpmjs.com/package/@wdio/mcp ↗통과
- 빌드 출처(Sigstore 증명)Sigstore attestation for @wdio/mcpnpmjs.com/package/@wdio/mcp/v/4.1.0#provenance ↗통과
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-11-15github.com/webdriverio/mcp ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음No popular package one edit away from @wdio/mcp통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음400 resolved dependencies checked; no critical advisoryosv.dev ↗통과
- 모델에 대한 숨겨진 지침 없음17 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨execute_script has no destructiveHint결함 발견
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기WebDriverIO MCP Server
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.
Installation
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"
]
}
}
}
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 mcp add wdio-mcp -- npx -y @wdio/mcp@latest
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"
]
}
}
}
Go to Cursor Settings → MCP → Add new MCP Server, or create .cursor/mcp.json:
{
"mcpServers": {
"wdio-mcp": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp@latest"
]
}
}
}
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"]
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
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"wdio-mcp": {
"command": "npx",
"args": [
"-y",
"@wdio/mcp@latest"
]
}
}
}
Edit Zed settings (~/.config/zed/settings.json):
{
"context_servers": {
"wdio-mcp": {
"source": "custom",
"command": "npx",
"args": [
"-y",
"@wdio/mcp@latest"
]
}
}
}
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.
Option 2: Global Installation
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.
HTTP Transport (for non-subprocess clients)
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.
Prerequisites For Mobile App Automation
- Appium Server: Install globally with
npm install -g appium - Platform Drivers:
- iOS:
appium driver install xcuitest(requires Xcode on macOS) - Android:
appium driver install uiautomator2(requires Android Studio)
- iOS:
- Devices/Emulators:
- iOS Simulator (macOS) or physical device
- Android Emulator or physical device
- For iOS Real Devices: You'll need the device's UDID (Unique Device Identifier)
- Find UDID on macOS: Connect device → Open Finder → Select device → Click device name/model to reveal UDID
- Find UDID on Windows: Connect device → iTunes or Apple Devices app → Click device icon → Click "Serial Number" to reveal UDID
- Xcode method: Window → Devices and Simulators → Select device → UDID shown as "Identifier"
Start the Appium server before using mobile features:
appium
# Server runs at http://127.0.0.1:4723 by default
Cloud Providers
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.
Prerequisites
Set your provider credentials as environment variables or in your MCP client config:
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"
}
}
}
}
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).
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) |
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) |
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.
Browser Sessions
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 flow'
}
})
// TestingBot
start_session({
provider: 'testingbot',
platform: 'browser',
browser: 'chrome',
os: 'Windows', // combined with osVersion → platformName (default: Windows 11)
osVersion: '11',
reporting: {
build: 'v1.2.0',
session: 'Login flow'
}
})
// Digital.ai
start_session({
provider: 'digitalai',
platform: 'browser',
browser: 'chrome',
os: 'Windows', // combined with osVersion → digitalai:osName (optional)
osVersion: '11',
reporting: {
session: 'Login flow' // → digitalai:testName (flat capability, not nested)
}
})
Provider-specific
os/osVersionbehavior:
- BrowserStack —
osandosVersionmap to separatebstack:options.os/bstack:options.osVersionfields.- Sauce Labs / LambdaTest / TestingBot —
osandosVersionare combined into the W3CplatformNamecapability (e.g.,os: 'Windows'+osVersion: '11'→platformName: 'Windows 11'). These providers useplatformNamevalues like"Windows 11","MacOS Sequoia", or"Linux". TestingBot defaults toWindows 11whenosis omitted.- Digital.ai —
osandosVersionare combined into the flatdigitalai:osNamecapability (NOTplatformName), e.g.os: 'Windows'+osVersion: '11'→digitalai:osName: 'Windows 11'.
Mobile App Sessions
Test on cloud real devices. First upload your app (or use an existing app URL):
// BrowserStack: returns bs:// URL
upload_app({ provider: 'browserstack', path: '/path/to/app.apk' })
// Sauce Labs: returns storage:filename= reference
upload_app({ provider: 'saucelabs', path: '/path/to/app.apk' })
// LambdaTest: returns lt:// URL
upload_app({ provider: 'testmu', path: '/path/to/app.apk' })
// TestingBot: returns tb:// URL
upload_app({ provider: 'testingbot', path: '/path/to/app.apk' })
// Digital.ai: returns cloud:<package-or-bundle> reference
upload_app({ provider: 'digitalai', path: '/path/to/app.apk' })
// Start a session
start_session({
provider: 'browserstack',
platform: 'android',
app: 'bs://abc123...',
deviceName: 'Samsung Galaxy S23',
platformVersion: '13.0'
})
// Sauce Labs native app
start_session({
provider: 'saucelabs',
platform: 'android',
app: 'storage:filename=myapp.apk',
deviceName: 'Samsung.*',
platformVersion: '16'
})
// LambdaTest native app
start_session({
provider: 'testmu',
platform: 'android',
app: 'lt://abc123...',
deviceName: 'Pixel 7',
platformVersion: '13'
})
// TestingBot native app
start_session({
provider: 'testingbot',
platform: 'android',
app: 'tb://abc123...',
deviceName: 'Pixel 7',
platformVersion: '13'
})
// Digital.ai native app — devices are selected via a deviceQuery
start_session({
provider: 'digitalai',
platform: 'android',
app: 'cloud:com.example.app',
deviceQuery: "@os='android' and @version='14' and @name='.*Pixel.*'"
// or omit deviceQuery and pass deviceName / platformVersion to build one
})
Mobile Browser Sessions
Run a browser on a cloud mobile device — real device or emulator/simulator — without uploading an app:
// BrowserStack — Chrome on Android emulator
start_session({
provider: 'browserstack',
platform: 'android',
browser: 'chrome',
deviceName: 'Google Pixel 7',
platformVersion: '13'
})
// Sauce Labs — Safari on iOS simulator
start_session({
provider: 'saucelabs',
platform: 'ios',
browser: 'safari',
deviceName: 'iPhone 15',
platformVersion: '18',
region: 'eu-central-1'
})
// LambdaTest — Chrome on Android emulator
start_session({
provider: 'testmu',
platform: 'android',
browser: 'chrome',
deviceName: 'Pixel 7',
platformVersion: '13'
})
// TestingBot — Chrome on Android emulator
start_session({
provider: 'testingbot',
platform: 'android',
browser: 'chrome',
deviceName: 'Pixel 7',
platformVersion: '13'
})
// Digital.ai — Chrome on an Android device (real or emulator; selected via a deviceQuery)
start_session({
provider: 'digitalai',
platform: 'android',
browser: 'chrome',
deviceName: 'Pixel 7',
platformVersion: '13'
// or omit deviceName / platformVersion and pass deviceQuery directly, e.g.
// deviceQuery: "@os='android' and @emulator='true'" to force an emulator
})
Note: Mobile browser sessions do not require
app,appPath, ornoReset. The provider launches a browser directly on the selected device — real or emulator/simulator.
Use list_apps to see previously uploaded apps:
list_apps({ provider: 'browserstack' })
list_apps({ provider: 'saucelabs', sortBy: 'app_name' })
list_apps({ provider: 'testmu' })
list_apps({ provider: 'testingbot' })
list_apps({ provider: 'digitalai' })
list_apps({ provider: 'browserstack', organizationWide: true })
Local Tunnel
To test against URLs that are only accessible on your local machine or internal network, enable a local tunnel:
// Auto-start tunnel (provider manages lifecycle)
start_session({
provider: 'saucelabs',
platform: 'browser',
tunnel: true // auto-starts tunnel before session
})
// Use an already-running tunnel
start_session({
provider: 'saucelabs',
platform: 'browser',
tunnel: 'external' // uses existing tunnel
})
The tunnel parameter replaces the deprecated browserstackLocal, saucelabsLocal, and testmuLocal params. Set it to true to auto-start the tunnel (stopped automatically after the session), or 'external' to use a tunnel already running on your machine.
Note: With
tunnel: truethe provider downloads and manages the tunnel binary for you. Fortunnel: 'external'you run it yourself — thewdio://saucelabs/local-binary,wdio://testmu/local-binary, andwdio://testingbot/local-binaryresources provide download URLs and setup instructions. The TestingBot Tunnel is a single cross-platform Java JAR (requires Java 11+) rather than a per-platform binary.
Reporting Labels
All session types support reporting labels that appear in the provider dashboard:
| Field | Description |
|---|---|
reporting.project |
Group sessions under a project name |
reporting.build |
Tag sessions with a build/version label |
reporting.session |
Name for the individual test session |
Cloud Provider Tools
| Tool | Description |
|---|---|
upload_app |
Upload a local .apk or .ipa to the provider; returns an app URL/reference |
list_apps |
List apps previously uploaded to the provider's app storage |
Both tools require a provider parameter ('browserstack', 'saucelabs', 'testmu', 'testingbot', or 'digitalai').
Features
Browser Automation
- Session Management: Start and close browser sessions (Chrome, Firefox, Edge, Safari) with headless/headed modes
- Navigation & Interaction: Navigate URLs, click elements, fill forms, and retrieve content
- Page Analysis: Get visible elements, accessibility trees, take screenshots
- Cookie Management: Get, set, and delete cookies
- Scrolling: Smooth scrolling with configurable distances
- Attach to running Chrome: Connect to an existing Chrome window via
--remote-debugging-port— ideal for testing authenticated or pre-configured sessions - Connect to existing WebDriver endpoints: Reuse an already-running Selenium-compatible WebDriver endpoint, such as a framework-managed browser or a desktop webview automation bridge (like Tauri)
- Device emulation: Apply mobile/tablet presets (iPhone 15, Pixel 7, etc.) to simulate responsive layouts without a physical device
- Session Recording: All tool calls are automatically recorded and exportable as runnable WebdriverIO JS
Mobile App Automation (iOS/Android)
- Native App Testing: Test iOS (.app/.ipa) and Android (.apk) apps via Appium
- Touch Gestures: Tap, swipe, long-press, drag-and-drop
- App Lifecycle: Launch, background, terminate, check app state
- Context Switching: Seamlessly switch between native and webview contexts for hybrid apps
- Device Control: Rotate, lock/unlock, geolocation, keyboard control, notifications
- Cross-Platform Selectors: Accessibility IDs, XPath, UiAutomator (Android), Predicates (iOS)
Available Tools
The server lists only the tools that fit the current session: browser sessions get the page tools below, mobile sessions the gestures and device tools, Electron sessions the Electron tools. Rarely used groups (mocks, cookies, device emulation, extensions, attaching, the raw element list, cloud app uploads) are listed after the agent calls enable_tools, so their definitions aren't sent with every request. With several live sessions, tools are listed for the union of their platforms. Set WDIO_MCP_TOOLS=all to list everything up front.
Set WDIO_MCP_NETWORK_LOGS to configure the default Chromium network/performance log capture mode for start_session: none (default, off), failures (Network.loadingFailed and Network.responseReceived entries with HTTP status >= 400), or all (every Chromium performance log entry). Individual sessions can override this default via start_session({ networkLogs: 'none' | 'failures' | 'all' }).
| Tool | Description |
|---|---|
enable_tools |
Add a group of tools: mocks, cookies, device, extensions, attach, elements, cloud-apps |
Session Management
| Tool | Description |
|---|---|
start_session |
Start a browser, local Electron application, or mobile app session; attach: true retains the existing Chrome CDP connection mode. Optional name and onExisting: "close" | "keep" (keep runs it alongside existing sessions; the new session is not made the default) |
attach_session |
Attach to an existing remote WebDriver/Appium session by sessionId without creating a new session; optional name and onExisting. With only a name, looks up a live session |
launch_chrome |
Launch a new Chrome instance with remote debugging enabled (for use with start_session({ attach: true })) |
close_session |
Close or detach from the default session, or the one named by the optional session target (supports detach: true to disconnect without terminating) |
emulate_device |
Emulate a mobile/tablet device preset (viewport, DPR, UA, touch); requires BiDi session |
open_web_extension |
Install a web extension through WebDriver BiDi and open one of its extension pages so normal page tools can drive its UI |
WebDriverIO MCP 질문
WebDriverIO MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add mcp -- npx -y @wdio/mcp를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
WebDriverIO MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
WebDriverIO MCP는 어떤 도구를 제공하나요?
17개 도구를 제공합니다. 예: start_session, close_session, navigate, switch_tab, switch_frame.
어떤 플랫폼을 자동화할 수 있나요?
Chrome, Firefox, Edge, Safari, Electron, iOS, Android를 자동화할 수 있습니다.
서브프로세스 클라이언트가 아닌 경우 HTTP transport를 어떻게 활성화하나요?
--http 플래그와 함께 포트를 지정하여 명령어를 실행하면 HTTP transport를 활성화할 수 있습니다.
클라우드 제공업체에서 테스트를 실행할 수 있나요?
네, 이 MCP server는 BrowserStack, Sauce Labs, LambdaTest, TestingBot, Digital.ai Testing을 지원합니다.