chrome-devtools-mcp
Chrome DevTools MCP — Google's official browser automation and testing server. Control Chrome via Puppeteer through MCP protocol: click, fill forms, navigate, screenshot, performance traces, network inspection, console debugging. Use for browser testing, web automation, performance analysis, UI testing, form filling, and visual regression.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aiwithabidi/chrome-devtools-mcpWhat This Skill Does
The chrome-devtools-mcp skill transforms your OpenClaw agent into a powerful browser-based automation powerhouse. By leveraging Google's official Chrome DevTools Protocol, it provides direct, programmatic control over a headless or headful Chrome instance. Whether you need to scrape complex dynamic websites, perform rigorous end-to-end UI testing, or manage complex web-based workflows, this skill allows the agent to interact with the web exactly like a human user would—only faster and with perfect precision. It bridges the gap between raw AI processing and the tangible reality of the modern web.
Installation
To integrate this skill into your environment, use the OpenClaw command-line interface or the automated setup script. First, ensure you have Node.js v20.19+ installed. Run the following command: clawhub install openclaw/skills/skills/aiwithabidi/chrome-devtools-mcp. For manual configuration, add the server definition to your openclaw.json file under the mcp.servers key, specifying your preferred flags such as --headless for server-side environments. You can also utilize the provided python setup scripts located in your base directory to automate configuration, status checks, and connectivity testing.
Use Cases
This skill is indispensable for professionals dealing with repetitive web tasks. Use it for automated UI regression testing to ensure design consistency across releases. It excels at web scraping, particularly for sites requiring JavaScript rendering. For developers, it provides deep visibility into network performance and console errors during runtime. It can also be used to fill out complex, multi-stage online forms, perform automated browser-based status reports, or generate visual snapshots of web applications for documentation purposes.
Example Prompts
- "Open Chrome to https://example.com, take a full-page screenshot, and identify any console errors reported during the page load."
- "Navigate to the login page of our internal portal, fill in the email and password fields using my credentials, and click the submit button. Wait until the dashboard loads."
- "Analyze the performance trace of the main homepage. Report back with the time-to-interactive metric and list any network requests that took longer than 500ms."
Tips & Limitations
To maximize reliability, always use the wait_for tool to handle dynamic content loading; trying to interact with elements before the DOM is ready is the most common cause of automation failures. Be mindful of website anti-bot protections; while this skill uses a legitimate Chrome instance, excessive rapid-fire interactions may trigger captchas. Always clean up sessions by closing pages you are done with to preserve system memory, especially when running in headless mode.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aiwithabidi-chrome-devtools-mcp": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, code-execution
Related Skills
freshsales
Freshsales CRM integration — manage contacts, leads, deals, accounts, tasks, and sales sequences via the Freshsales API. Track deal pipelines, automate lead assignments, log activities, and generate sales reports. Built for AI agents — Python stdlib only, no dependencies. Use for sales CRM, contact management, deal tracking, pipeline reporting, and sales automation.
gemini-video-analyzer
Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.
agent-memory
Full AI agent memory stack — Mem0 unified memory engine with vector search (Qdrant) and knowledge graph (Neo4j), plus SQLite for structured data. Complete setup script and tools. Give your OpenClaw agent a real brain with semantic recall, entity relationships, and structured storage.
neon
Neon serverless Postgres — manage projects, branches, databases, roles, endpoints, and compute via the Neon API. Create database branches for development, manage connection endpoints, scale compute, and monitor usage. Built for AI agents — Python stdlib only, zero dependencies. Use for serverless Postgres, database branching, database management, development workflows, and cloud database automation.
onepassword
1Password Connect — vaults, items, secrets management for server-side applications.