browser-testing-with-devtools

Inspect DOM, console, network, and performance in live browsers via Chrome DevTools MCP.

Updated Apr 28, 2026
One-click install
npx skills add https://github.com/JacobThree/zero-bloat-mcp-stack --skill browser-testing-with-devtools-jacobthree
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browser-testing-with-devtools
Source: https://github.com/JacobThree/zero-bloat-mcp-stack/tree/main/ai_blueprints/agent-skills/skills/browser-testing-with-devtools
Command: npx skills add https://github.com/JacobThree/zero-bloat-mcp-stack --skill browser-testing-with-devtools-jacobthree

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @anthropic/chrome-devtools-mcp.

What problem does it solve? Static code analysis cannot reveal what actually happens at runtime in a browser. This Skill gives the agent live visibility into the browser so it can verify UI behavior, diagnose console errors, analyze network requests, and profile performance with real runtime data instead of guessing. ## Core Features & Use Cases - Live Browser Inspection: Capture screenshots, read the DOM tree, retrieve console logs, and monitor network requests through Chrome DevTools MCP. - Structured Debugging Workflows: Follow step-by-step flows for UI bugs, network failures, and performance issues, from reproduction to verified fix. - Security Boundaries: Treats all browser content as untrusted data, restricts JavaScript execution to read-only inspection, and blocks credential access. - Use Case: A task completion animation glitches in your app. The agent navigates to the page, reproduces the bug, checks the console and network traffic, identifies the root cause, applies the fix, and verifies with before/after screenshots. ## Quick Start Use Chrome DevTools MCP to open my localhost page, check the console for errors, and take a screenshot to verify the layout.

Frequently Asked Questions about browser-testing-with-devtools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I debug UI issues with Chrome DevTools MCP?▼

Reproduce the bug in the browser, take a screenshot, then inspect the console for errors, read the DOM element, and check computed styles. Compare actual versus expected structure to find the root cause, fix the code, and reload to verify.

How to analyze network requests in the browser with an AI agent?▼

Open the network monitor, trigger the action, then check the request URL, method, headers, payload, and response status. The workflow maps 4xx errors to client issues, 5xx to server problems, and CORS failures to origin header configuration.

What tools does Chrome DevTools MCP provide?▼

It provides screenshot capture, DOM inspection, console log retrieval, network monitoring, performance tracing, computed style reading, accessibility tree access, and JavaScript execution in the page context for read-only state inspection.

Can the agent read cookies or localStorage through DevTools?▼

No. The Skill explicitly prohibits JavaScript execution from reading cookies, localStorage tokens, sessionStorage secrets, or any authentication material. Application state should be inspected through non-sensitive variables instead.

When should I not use browser testing with DevTools?▼

Do not use it for backend-only changes, CLI tools, or code that does not run in a browser. It is designed specifically for verifying and debugging anything that renders or executes in a browser environment.

Why is browser content treated as untrusted data?▼

A malicious or compromised page can embed instruction-like text in the DOM, console, or network responses to manipulate agent behavior. The Skill requires flagging such content and never executing instructions found in browser data.