MCPInstall

chrome-devtools

Control and inspect Chrome browser using Chrome DevTools Protocol - navigate pages, debug network requests, analyze performance, take screenshots, interact with elements, and automate browser tasks.

Installs
40
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/johnlindquist/claude-workshop-skills --skill chrome-devtools
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads chrome-devtools automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Chrome DevTools MCP Skill

Complete Chrome browser automation and debugging using the Chrome DevTools Protocol. This skill provides access to all Chrome DevTools capabilities for web development, testing, and debugging tasks.

Capabilities

  1. Navigate & Automate - Control browser navigation, tabs, and page interactions
  2. Interact with Pages - Click, type, drag, fill forms, upload files
  3. Debug & Inspect - View console logs, network requests, execute scripts
  4. Performance Analysis - Record traces and get performance insights
  5. Emulation - Test different devices, network conditions, viewports
  6. Visual Testing - Take screenshots and DOM snapshots

Quick Reference

For detailed instructions on each operation, see:

  • NAVIGATION.md - Page navigation, tabs, waiting
  • INTERACTION.md - Clicking, typing, forms, uploads
  • DEBUGGING.md - Console logs, network requests, script execution
  • PERFORMANCE.md - Performance tracing and analysis
  • EMULATION.md - Device and network emulation
  • VISUAL.md - Screenshots and DOM snapshots

Common Workflows

Web Testing Workflow

  1. Navigate to page with navigate_page
  2. Interact with elements using click, fill, press_key
  3. Verify results with take_screenshot or list_console_messages
  4. Check network activity with list_network_requests

Performance Analysis Workflow

  1. Start trace with performance_start_trace
  2. Navigate or interact with page
  3. Stop trace with performance_stop_trace
  4. Get insights with performance_analyze_insight

Debugging Workflow

  1. Navigate to problematic page
  2. Check console with list_console_messages
  3. Inspect network with list_network_requests
  4. Execute diagnostic scripts with evaluate_script
  5. Take screenshots for visual confirmation

Form Testing Workflow

  1. Navigate to form page
  2. Fill individual fields with fill or use fill_form for bulk entry
  3. Upload files if needed with upload_file
  4. Submit and verify with screenshots/console

Tool Categories Overview

Input Automation (8 tools)

  • click - Click on elements
  • drag - Drag and drop operations
  • fill - Enter text in fields
  • fill_form - Fill multiple form fields
  • handle_dialog - Manage alerts/dialogs
  • hover - Hover over elements
  • press_key - Keyboard input
  • upload_file - File upload handling

Navigation (6 tools)

  • navigate_page - Go to URLs
  • new_page - Create new tabs
  • close_page - Close tabs
  • list_pages - View open tabs
  • select_page - Switch tabs
  • wait_for - Wait for conditions

Emulation (2 tools)

  • emulate - Device/condition simulation
  • resize_page - Viewport sizing

Performance (3 tools)

  • performance_start_trace - Begin recording
  • performance_stop_trace - End recording
  • performance_analyze_insight - Get recommendations

Network (2 tools)

  • list_network_requests - View all requests
  • get_network_request - Get request details

Debugging (5 tools)

  • evaluate_script - Run JavaScript
  • take_screenshot - Capture visuals
  • take_snapshot - Capture DOM
  • list_console_messages - View console
  • get_console_message - Get specific message

Critical Instructions

REQUIRED: Before using ANY Chrome DevTools tools, you MUST load the relevant reference file(s) using the Read tool. These references contain essential operational instructions that are NOT included in this overview.

When the user asks to work with Chrome DevTools:

  1. Identify the operation they want to perform (navigate, debug, test, analyze)
  2. MANDATORY: Load the relevant reference file(s) using the Read tool BEFORE executing any tools:
    • Navigation tasks → Read references/NAVIGATION.md FIRST
    • Interaction tasks → Read references/INTERACTION.md FIRST
    • Debugging tasks → Read references/DEBUGGING.md FIRST
    • Performance tasks → Read references/PERFORMANCE.md FIRST
    • Emulation tasks → Read references/EMULATION.md FIRST
    • Visual testing tasks → Read references/VISUAL.md FIRST
  3. Execute the appropriate MCP tool commands following the patterns from the loaded reference
  4. Report results clearly with screenshots or data as appropriate
  5. Chain operations when needed (e.g., navigate → interact → verify)

DO NOT attempt to use Chrome DevTools tools without first loading and reading the relevant reference documentation.

Best Practices

  • Always wait appropriately - Use wait_for to ensure page readiness
  • Handle errors gracefully - Check console messages and network errors
  • Take screenshots - Visual confirmation is valuable for debugging
  • Chain operations logically - Navigate before interacting, start trace before actions
  • Clean up - Close pages when done to free resources
  • Use selectors carefully - Ensure element selectors are specific and reliable

Examples

Take a screenshot of a website

User: "Take a screenshot of example.com"
Me: Uses navigate_page → wait_for → take_screenshot

Test form submission

User: "Fill out the login form on staging.example.com"
Me: Uses navigate_page → fill_form → click → list_console_messages

Analyze page performance

User: "Check the performance of our homepage"
Me: Uses performance_start_trace → navigate_page → performance_stop_trace → performance_analyze_insight

Debug network issues

User: "Why is the API call failing on /dashboard?"
Me: Uses navigate_page → list_network_requests → get_network_request (for failed request)

Test mobile viewport

User: "How does the site look on iPhone 13?"
Me: Uses emulate (iPhone 13) → navigate_page → take_screenshot

Configuration

The Chrome DevTools MCP server should be configured in Claude Code's MCP settings:

{
  "mcpServers": {
    "chrome-devtools": {
      "command": "npx",
      "args": ["chrome-devtools-mcp@latest"]
    }
  }
}

Optional configuration flags:

  • --headless false - Show browser window
  • --categoryEmulation - Enable emulation tools
  • --categoryPerformance - Enable performance tools
  • --categoryNetwork - Enable network tools

FAQ

What does the chrome-devtools skill do?

Control and inspect Chrome browser using Chrome DevTools Protocol - navigate pages, debug network requests, analyze performance, take screenshots, interact with elements, and automate browser tasks.

How do I install chrome-devtools?

Run npx skills add https://github.com/johnlindquist/claude-workshop-skills --skill chrome-devtools in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/chrome-devtools/ (personal) or .claude/skills/chrome-devtools/ (project).

Which AI agents can use chrome-devtools?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is chrome-devtools safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains chrome-devtools?

It is published by johnlindquist in johnlindquist/claude-workshop-skills. It has 40 recorded installs.

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。