This project is no longer under active development. The official WebDriverIO MCP server is now available as @wdio/mcp, which was built using this project as its foundation.
webdriverio-mcp is an MCP project maintained in the winify/webdriverio-mcp repository. The maintainer describes its purpose as “This project is no longer under active development. The official WebDriverIO MCP server is now available as @wdio/mcp, which was built using this project as…”. Read the project documentation for the complete scope.
The documented npm package is webdriverio-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| start_browser | Start a Chrome browser session (headless/headed, custom dimensions) |
| start_app_session | Start an iOS or Android app session via Appium (supports state preservation via noReset) |
| close_session | Close or detach from the current browser or app session (supports detach mode) |
| navigate | Navigate to a URL |
| get_visible_elements | Get visible, interactable elements on the page. Supports inViewportOnly (default: true) to filter viewport elements, and includeContainers (default: false)… |
| get_accessibility | Get accessibility tree with semantic element information |
| scroll_down | Scroll down by specified pixels |
| scroll_up | Scroll up by specified pixels |
| take_screenshot | Capture a screenshot |
| find_element | Find an element using CSS selectors, XPath, or mobile selectors |
| click_element | Click an element |
| click_via_text | Click an element by text content |
| set_value | Type text into input fields |
| get_element_text | Get text content of an element |
| is_displayed | Check if an element is displayed |
| get_cookies | Get all cookies or a specific cookie by name |
| set_cookie | Set a cookie with name, value, and optional attributes |
| delete_cookies | Delete all cookies or a specific cookie |
| tap_element | Tap an element by selector or coordinates |
| swipe | Swipe in a direction (up/down/left/right) |
| long_press | Long press an element or coordinates |
| drag_and_drop | Drag from one location to another |
| get_app_state | Check app state (installed, running, background, foreground) |
| activate_app | Bring app to foreground |
| terminate_app | Terminate a running app |
| get_contexts | List available contexts (NATIVE_APP, WEBVIEW_) |
| get_current_context | Show the currently active context |
| switch_context | Switch between native and webview contexts |
| get_device_info | Get device platform, version, screen size |
| rotate_device | Rotate to portrait or landscape orientation |
| get_orientation | Get current device orientation |
| is_device_locked | Check if device is locked |
| shake_device | Shake the device (iOS only) |
| send_keys | Send keyboard input (Android only) |
| press_key_code | Press Android key code (BACK=4, HOME=3, etc.) |
| open_notifications | Open notifications panel (Android only) |
{
"mcpServers": {
"webdriverio-mcp": {
"command": "npx",
"args": [
"-y",
"webdriverio-mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript