도구

A disciplined process for hard bugs and performance regressions: build a reliable reproduction loop, reproduce and minimize, form hypotheses, instrument to verify, then fix and add a regression test, redacting secrets in output. By Matt Pocock.

Teaches agents to use the Chrome DevTools MCP efficiently: snapshot first to get element uids, screenshot only when needed, paginate and filter large output, inspect CSS and test browser extensions. Needs chrome-devtools-mcp configured; maintained by the Chrome DevTools team.

Lets agents control and inspect a real Chrome: read the console and network requests, take screenshots, and record performance traces with optimization suggestions. Maintained by the Chrome DevTools team.

Official Chrome plugin bundling the Chrome DevTools MCP with debugging skills for accessibility, LCP and memory leaks: lets agents drive and inspect a real Chrome and analyze network requests, console logs and performance traces. Collects usage stats by default; can be disabled.

Orchestrates multi-agent teams using Claude Code's experimental Agent Teams feature: parallel multi-angle code review, competing-hypothesis debugging and feature work split by file ownership. Enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS first.

Connects to the Arize Phoenix observability platform so agents can query LLM traces and sessions, manage prompts, browse datasets and read experiment evaluation results. Maintained by Arize; needs a self-hosted or cloud Phoenix instance.

The official MCP debugging tool: connect to any MCP server through a web UI, CLI or terminal UI to list and call its tools, resources and prompts. CLI mode outputs JSON, suited to scripts and CI smoke tests.

Tencent's open-source browser bridge: through the bsk CLI and a Chrome/Edge extension, agents use your logged-in accounts in a separate visible window to browse, fill forms and take full-page screenshots, and correlate network requests with console output to debug sites.

Tests and debugs a locally running frontend with Codex's Browser plugin or Playwright: checks blank pages, framework and console errors, captures screenshots, re-verifies after fixes and writes a QA report. Maintained by OpenAI; formerly playwright-interactive in openai/skills.

Hands your current browser session to the agent through a Chrome extension: read console logs and network requests, take screenshots, and run Lighthouse performance, accessibility and SEO audits without signing in again.

Lets coding agents control real Chrome with short Puppeteer scripts, with named pages that keep state across calls, accessibility-tree snapshots and screenshots for self-testing web changes. Install the dev-browser CLI globally first; macOS and glibc Linux only.

Lets agents build, run, test and debug iOS and macOS projects and control simulators and physical devices, with a CLI mode too. Formerly XcodeBuildMCP, now maintained by Sentry; macOS only, requires Xcode 16 or later.

From Callstack: lets coding agents inspect, operate and verify apps on iOS, Android and HarmonyOS simulators and real devices, reading accessibility snapshots, taking screenshots and recordings, and capturing logs and performance data. Ships both a CLI and a built-in MCP server.

From Callstack: lets coding agents drive and verify iOS, Android, HarmonyOS and desktop apps through accessibility snapshots, with taps, form filling, screenshots, logs and performance sampling, plus a built-in MCP server. Requires Node.js 22.12+.

LogRocket's official plugin: when users report problems, agents pull up their session replays, network requests and errors and analyze the cause, so support doesn't have to keep asking for repro steps. Needs Claude Code and a site or app on paid LogRocket (14-day trial); sign in on first use.