testing MCP Server
Playwright MCP server
Discovered via unknown and last synced 3mo ago.
1. Install the package
npx @playwright/mcp
2. Add to claude_desktop_config.json
{
"mcpServers": {
"playwright-mcp-internal": {
"command": "npx",
"args": [
"@playwright/mcp"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
QA engineers and test automation developers who need to interact with web applications programmatically during testing. Frontend developers building integration tests benefit from precise element interaction capabilities. Teams using Claude AI as a coding assistant gain the ability to automate complex browser interactions through natural language.
Chain multiple interactions like clicks, typing, and scrolling to simulate realistic user journeys. Capture element references from page snapshots to ensure reliable element targeting across test runs.
Use exact element references and coordinates to identify why interactions fail. Compare snapshots before and after actions to verify page state changes.
Describe test scenarios to Claude, which translates them into playwright interactions using tool parameters. Reduces boilerplate while maintaining precise element targeting via ref attributes.
Interact with complex inputs requiring keyboard modifiers or delta-based scrolling. Test accessibility features and keyboard-driven interfaces systematically.
Use the exact `ref` parameter from the page snapshot—each element has a unique reference string. For complex selections, provide both `startRef` and `endRef` to define a precise interaction range.
Yes. Use `startX`, `startY`, and `deltaY` parameters for pixel-level control. This is especially useful for drag operations, scrolling, or clicking specific positions within large elements.
Provide Claude with your page snapshot and describe your test scenario in plain language. Claude uses the tool parameters to generate executable playwright commands with accurate element references and coordinates.
Element references may become invalid if the DOM changes significantly. Always capture fresh snapshots before running interactions, and use `endElement` descriptions to help identify elements if references drift.
(string, optional): The text of the prompt in case of a prompt dialog.
generated by update-readme.js -->
(string): Exact source element reference from the page snapshot
(string): Human-readable target element description used to obtain the permission to interact with the element
(string): Exact target element reference from the page snapshot
(number): Start X coordinate
This has been generated via update-readme.js -->
(string): Exact target element reference that points to the element
(array, optional): Modifier keys to press
(number): Y delta
(boolean, optional): Whether to submit entered text (press Enter after)
(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.
Verify value
(string): Human-readable element description
of tools generated section -->
(number, optional): Tab index, used for close/select. If omitted for close, current tab is closed.
(number): X coordinate
(number): Height of the browser window
(boolean, optional): When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
(string): ACCESSIBLE_NAME of the element. Can be found in the snapshot like this: `- role "{ACCESSIBLE_NAME}"`
(array): Items to verify
(array): Array of values to select in the dropdown. This can be a single value or multiple values.
Verify element value
- `type` (string): Type of the element
(string): Value to verify. For checkbox, use "true" or "false".
(string, optional): The text to wait for
(string, optional): The text to wait for to disappear
(number): Start Y coordinate
(string, optional): File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified. Prefer relative file names to stay within the output directory.
(number): End X coordinate
(number): End Y coordinate
(boolean, optional): Whether to perform a double click instead of a single click
(string, optional): Button to click, defaults to left
(number): Y coordinate
Production-grade test automation skills for 46 frameworks across E2E, unit, mobile, BDD, visual, and cloud testing in 15+ languages.
Audit a live web page in five phases (catalog, click, trace, classify, report) to identify mock data, hardcoded values, LLM-generated metrics, and broken endpoints. Outputs a markdown report with REAL/MOCK/LLM/HARDCODED/BROKEN/UNKNOWN verdicts per visible value.
X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.
Proves work with tests, diffs, and logs before sign-off.
Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.
AgentEval is the comprehensive .NET toolkit for AI agent evaluation—tool usage validation, RAG quality metrics, stochastic evaluation, and model comparison—built first for Microsoft Agent Framework (MAF) and Microsoft.Extensions.AI. What RAGAS, PromptFoo and DeepEval do for Python, AgentEval does for .NET
Cognitive Browser: The browser automation that thinks. Constitutional safety • Persona UX testing • Natural language interface • Self-healing selectors • Built for AI agents
Learn how to use the absolute-deflake Claude skill. Complete guide with installation instructions and examples.
Learn how to use the prompt-reliability-engine Claude skill. Complete guide with installation instructions and examples.
Learn how to use the expect Claude skill. Complete guide with installation instructions and examples.