chrome-devtools-mcp-automation

Automate Chrome browser navigation, debugging, and performance analysis via MCP.

7|2|Updated May 16, 2026
One-click install
npx skills add https://github.com/Aradotso/mcp-skills --skill chrome-devtools-mcp-automation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chrome-devtools-mcp-automation
Source: https://github.com/Aradotso/mcp-skills/tree/main/skills/chrome-devtools-mcp-automation
Command: npx skills add https://github.com/Aradotso/mcp-skills --skill chrome-devtools-mcp-automation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates slow, error-prone manual browser debugging and performance investigation by letting an AI agent navigate, observe, and instrument Chrome via the DevTools interface.

Core Features & Use Cases

  • Browser automation for real sites: Navigate, click, type, and extract content so you can reproduce issues and complete UI flows reliably.
  • Debugging with high-fidelity signals: Inspect network activity (including failed requests) and capture console errors to diagnose production problems.
  • Performance analysis and Core Web Vitals: Record traces and compute metrics (optionally including CrUX data) to validate improvements and regressions.
  • Use Case: When a checkout page fails intermittently, you can reproduce the flow, collect failed network requests, capture console errors, and produce performance traces and metrics for root-cause analysis.

Quick Start

Use the chrome-devtools-mcp automation Skill to navigate to https://example.com, capture screenshots, and report any console errors and failed network requests.

Frequently Asked Questions about chrome-devtools-mcp-automation

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

FAQPage Schema
How do I automate Chrome DevTools to capture network requests and console errors?

You can automate Chrome DevTools to capture network requests and console errors by using an AI agent over MCP to navigate URLs, filter network activity, and extract console logs for debugging production issues.

Can I measure Core Web Vitals and record performance traces using browser automation?

Yes, you can measure Core Web Vitals and record performance traces through browser automation by directing an AI agent to instrument Chrome via DevTools, optionally collecting CrUX data to validate performance regressions.

What is the best way to reproduce an intermittent UI failure and collect screenshot evidence?

The best way to reproduce intermittent UI failures and collect screenshot evidence is automating deterministic browser navigation over MCP to click, type, capture screenshots, and log console errors during the exact failure flow.

Do I need a Chrome DevTools MCP server to run browser debugging workflows?

Yes, you need a Chrome DevTools MCP server configured in standard or slim mode to enable AI agents to execute tool-driven actions, network inspection, and trace collection for debugging workflows.

How does AI agent browser automation over MCP compare to manual Chrome debugging?

AI agent browser automation over MCP eliminates slow manual debugging by deterministically navigating real sites, inspecting failed network requests, and computing trace metrics, whereas manual debugging relies on error-prone human observation.

Why would network inspection not capture failed requests during automated UI testing?

Network inspection might not capture failed requests during automated UI testing if the Chrome DevTools MCP server is running in slim mode, which may limit full network filtering capabilities required for complete request interception.