A high-performance browser automation skill that enables AI agents to interact with websites, fill forms, and extract data via the Playwright framework.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pascal-playwright-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pascal-playwright-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Playwright MCP?
The Playwright MCP skill is a robust automation engine designed to give AI agents full control over web browsers. By leveraging the Model Context Protocol, this skill allows agents to perform complex tasks such as navigating dynamic websites, interacting with UI elements, and executing custom JavaScript. It is an essential component for developers building sophisticated agents within the Openclaw Skills ecosystem that require real-time web access.
Whether you are automating repetitive web tasks or building a research agent, Playwright MCP provides the necessary tools to bridge the gap between LLMs and the live web. It supports multiple browser engines, including Chromium, Firefox, and WebKit, ensuring compatibility across the entire modern web landscape.
Playwright MCP Use Cases
- Automating multi-step authentication and login flows on enterprise web portals.
- Scraping structured data from dynamic, JavaScript-heavy Single Page Applications (SPAs).
- Performing automated UI testing and capturing visual snapshots for regression monitoring.
- Conducting deep-web research by navigating across multiple domains to aggregate specific technical data.
How Playwright MCP Works
- The AI agent initiates the Playwright MCP server using a standard STDIO connection.
- The agent issues a navigation command to open a target URL in a headless or headed browser instance.
- User-defined tools like browser_click or browser_type are invoked to interact with the DOM based on CSS or XPath selectors.
- For advanced data retrieval, the browser_evaluate tool runs custom scripts directly in the page context to return JSON data.
- The session can be finalized by taking a screenshot or generating a full page snapshot before closing the browser context.
Playwright MCP Setup
To begin using this skill, install the core package and the necessary browser binaries:
npm install -g @playwright/mcp
npx playwright install chromium
Launch the server to integrate it with your agent environment:
npx @playwright/mcp --headless
Playwright MCP Data Schema & Taxonomy
The skill utilizes a structured toolset to manage browser interactions. Below is a summary of the data handled by the core tools:
| Tool Name | Key Parameters | Expected Output |
|---|---|---|
browser_navigate |
url |
Load status and final URL |
browser_snapshot |
selector |
Accessibility tree or DOM structure |
browser_evaluate |
script |
Result of the JavaScript execution |
browser_type |
selector, text |
Confirmation of input |
browser_click |
selector |
Interaction success flag |
Playwright MCP Advanced Features
- Cross-browser support for Chromium, Firefox, and WebKit engines for comprehensive testing.
- Granular security controls including domain whitelisting via --allowed-hosts to ensure safe Openclaw Skills execution.
- Integrated media recording capabilities for capturing browser traces, videos, and high-resolution screenshots.
- Customizable viewport dimensions and User-Agent strings to emulate various device environments.
- Configurable navigation and action timeouts to handle slow-loading enterprise applications.
SKILL.md
Loading
Related Openclaw Skills
Self-Evolving Agent
A meta-analytical automation tool that observes AI agent performance and suggests optimized instruction updates based on semantic log patterns and real-time monitoring.
OpenClaw Self-Healing System
An autonomous 4-tier recovery system that monitors gateway health and uses AI to diagnose and repair persistent failures.
MemoryBox
MemoryBox is a zero-dependency CLI tool designed to maintain a lean 3-tier hierarchical memory structure for Openclaw Skills.
Skill Optimizer
An automated diagnostic tool that analyzes AI conversation logs to evaluate performance and generate data-driven optimizations for agent skills.
Step ASR
A high-performance audio transcription tool that converts Chinese and English speech into text using the StepFun streaming API.
Skill Deps Doctor
A cross-platform dependency validator designed to ensure all system-level and project-level requirements are met for Openclaw Skills.
METADATA
Featured*
