Standard I/O
Docker
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"-playwright-mcp": {
"args": [
"index.js"
],
"command": "node"
}
}
}(string, optional): Button to click, defaults to left
(string): Exact target element reference from the page snapshot
generated by update-readme.js -->
(string): Exact source element reference from the page snapshot
(array, optional): Modifier keys to press
(string): Human-readable element description
(number): Height of the browser window
(string, optional): The text to wait for
(string, optional): File name to save the screenshot to. Relative file names are resolved against the workspace root. If not specified, the screenshot is saved into the output directory as `page-{timestamp}.{png|jpeg|webp}`.
(boolean, optional): Whether to perform a double click instead of a single click
(string, optional): The text of the prompt in case of a prompt dialog.
Verify value
(boolean, optional): Whether to submit entered text (press Enter after)
(string, optional): The text to wait for to disappear
(string, optional): Human-readable target element description used to obtain the permission to interact with the element
(array): Array of values to select in the dropdown. This can be a single value or multiple values.
This has been generated via update-readme.js -->
(number): End Y coordinate
(string, optional): Comma-separated list of header names to remove from request
(string): ACCESSIBLE_NAME of the element. Can be found in the snapshot like this: `- role "{ACCESSIBLE_NAME}"`
(number): X coordinate
(number): Y coordinate
(string, optional): Chapter description
(string): Exact target element reference that points to the element
(number, optional): Tab index, used for close/select. If omitted for close, current tab is closed.
(number): End X coordinate
(string): Exact target element reference from the page snapshot
(string, optional): Pause execution at a specific <file>:<line>, e.g. "example.spec.ts:42".
(object, optional): Styles of the action decorations.
(string): Exact target element reference from the page snapshot, or a unique element selector
(string, optional): Cookie path
(string, optional): URL to navigate to in the new tab, used for new.
(number, optional): Duration in milliseconds to show the chapter card
(string): Exact target element reference from the page snapshot, or a unique element selector
(string, optional): Cookie domain
(array, optional): Absolute paths to files to drop onto the element.
(array, optional): Headers to add in "Name: Value" format
of tools generated section -->
(number): Y delta
(string): () => { /* code */ } or (element) => { /* code */ } when element is provided
(string, optional): Only return requests whose URL matches this regexp (e.g. "/api/.*user").
(number, optional): HTTP status code to return (default: 200)
(boolean, optional): Whether the cookie is HTTP only
(boolean): Whether to include request body. Defaults to false.
(number, optional): Number of clicks, defaults to 1
(boolean): Whether to include request headers. Defaults to false.
(string, optional): Content-Type header (e.g., "application/json", "text/html")
(object, optional): Video size
(boolean, optional): Whether the cookie is secure
(string, optional): Return only this part of the request. Omit to return full details.
(number): Start X coordinate
(array): Items to verify
(string, optional): Response body (text or JSON string)
(string, optional): Image format for the screenshot. If unset, inferred from the filename extension, otherwise png.
(number): Start Y coordinate
(boolean, optional): Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect)
(object, optional): Data to drop, as a map of MIME type to string value (e.g. {"text/plain": "hello", "text/uri-list": "https://example.com"}).
(string, optional): Cookie SameSite attribute
(number, optional): Cookie expiration as Unix timestamp
(number, optional): Time to wait between mouse down and mouse up in milliseconds, defaults to 0
(string): Value to verify. For checkbox, use "true" or "false".
(number, optional): Limit the depth of the snapshot tree
(string, optional): Name of an isolated browser context to create the new tab in, used for new. Tabs in the same isolated context share cookies and storage, tabs in different contexts are fully isolated. If omitted or "default", the tab is created in the default context.
(optional): Changes the CSS media type of the page
(number, optional): Video frame rate in frames per second, defaults to 25
(string, optional): Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. "/error/i" for case-insensitive. Provide either text or regex, not both.
(string): Image resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for the device pixel ratio). Default is css.
(string, optional): Cursor decoration for pointer actions. "pointer" (default) animates a mouse pointer from the previous action point to the next one; "none" disables the cursor decoration.
(boolean, optional): Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.
(number, optional): Maximum number of matching items to return. Defaults to returning all matches.
(boolean, optional): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
(boolean, optional): Return all network requests since the beginning of the session, not just since the last navigation. Defaults to false.
(optional): Emulates the prefers-reduced-motion media feature
(object, optional): Input parameters for the tool, matching its inputSchema
(string, optional): Frame that registered the tool, as reported by browser_webmcp_list, when the same tool name exists in multiple frames
(optional): Emulates the forced-colors media feature
(string, optional): Where to place the action title relative to the page. Defaults to top-right.
(optional): Emulates the prefers-contrast media feature
Verify element value
- `type` (string): Type of the element
Evaluate and compare ML model performance with rigorous testing methodologies
Automated testing agent that executes complete roundtrip workflow tests for MCP elements
Skill for creating comprehensive documentation of GitHub and DollhouseMCP integration workflows
Generate comprehensive test suites including unit tests, integration tests, and E2E tests