← 返回 Skills 市场

Luke Chrome Devtools Mcp

Name: Luke Chrome Devtools Mcp
Author: banalit

作者 banalit · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

360

总下载

当前安装

版本数

在 OpenClaw 中安装

/install luke-chrome-devtools-mcp

功能描述

Chrome DevTools MCP — Google's official browser automation and testing server. Control Chrome via Puppeteer through MCP protocol: click, fill forms, navigate...

使用说明 (SKILL.md)

🌐 Chrome DevTools MCP

Google's official Chrome DevTools MCP server — gives AI agents full control of a live Chrome browser via Puppeteer and the Chrome DevTools Protocol.

Features

Input automation — click, drag, fill forms, hover, press keys, upload files, handle dialogs
Navigation — open/close/switch pages, wait for elements/network idle
Screenshots & snapshots — capture page state visually and as DOM
Performance traces — record and analyze Chrome performance traces with insights
Network inspection — list/inspect network requests and responses
Console debugging — read console messages with source-mapped stack traces
Device emulation — emulate mobile devices, resize viewport
Form automation — fill multiple form fields at once

Requirements

Node.js v20.19+ (already available in OpenClaw)
Chrome/Chromium browser

Quick Start

Install & verify

npx -y chrome-devtools-mcp@latest --help

Start the MCP server

# Standard (launches Chrome automatically)
npx -y chrome-devtools-mcp@latest

# Headless mode (for servers)
npx -y chrome-devtools-mcp@latest --headless

# Connect to existing Chrome (must be started with --remote-debugging-port=9222)
npx -y chrome-devtools-mcp@latest --browser-url=http://127.0.0.1:9222

# Disable telemetry
npx -y chrome-devtools-mcp@latest --no-usage-statistics --no-performance-crux

OpenClaw MCP Integration

Add to your openclaw.json under MCP servers:

{
  "mcp": {
    "servers": {
      "chrome-devtools": {
        "command": "npx",
        "args": ["-y", "chrome-devtools-mcp@latest", "--headless", "--no-usage-statistics"]
      }
    }
  }
}

Or use the setup script:

python3 {baseDir}/scripts/setup_chrome_mcp.py setup
python3 {baseDir}/scripts/setup_chrome_mcp.py status
python3 {baseDir}/scripts/setup_chrome_mcp.py test

Tool Reference

Input Automation (8 tools)

Tool	Description	Key Params
`click`	Click an element	`uid` (required), `dblClick`
`drag`	Drag element onto another	`from_uid`, `to_uid`
`fill`	Type text into input/textarea/select	`uid`, `value`
`fill_form`	Fill multiple form elements at once	`elements[]`
`handle_dialog`	Accept/dismiss browser dialogs	`action` (accept/dismiss)
`hover`	Hover over element	`uid`
`press_key`	Press keyboard key	`key`
`upload_file`	Upload file to input	`uid`, `paths[]`

Navigation (6 tools)

Tool	Description	Key Params
`navigate_page`	Go to URL	`url`
`new_page`	Open new tab	`url`
`close_page`	Close current tab	—
`list_pages`	List all open tabs	—
`select_page`	Switch to tab	`index`
`wait_for`	Wait for element/network	`event`, `uid`, `timeout`

Debugging (5 tools)

Tool	Description
`take_screenshot`	Capture page as image
`take_snapshot`	Get DOM/accessibility snapshot
`evaluate_script`	Run JavaScript in page
`list_console_messages`	Get console log entries
`get_console_message`	Get specific console message

Performance (3 tools)

Tool	Description
`performance_start_trace`	Begin performance recording
`performance_stop_trace`	Stop and get trace data
`performance_analyze_insight`	AI analysis of trace

Network (2 tools)

Tool	Description
`list_network_requests`	List all network requests
`get_network_request`	Get request/response details

Emulation (2 tools)

Tool	Description
`emulate`	Emulate device (mobile, tablet)
`resize_page`	Change viewport size

Common Workflows

Test a webpage

navigate_page → URL
take_snapshot → get element UIDs
click/fill → interact with elements
take_screenshot → capture result

Performance audit

navigate_page → URL
performance_start_trace
Interact with page
performance_stop_trace
performance_analyze_insight

Form testing

navigate_page → form URL
take_snapshot → identify form fields
fill_form → fill all fields at once
click → submit button
take_screenshot → verify result

Privacy Notes

Google collects usage statistics by default — disable with --no-usage-statistics
Performance tools may send trace URLs to Google CrUX API — disable with --no-performance-crux
Avoid sharing sensitive data in browser sessions

安全使用建议

This skill appears coherent for running Chrome DevTools MCP, but take these precautions before installing: 1) npx -y ...@latest downloads and runs the latest npm package — pin to a specific version ([email protected]) if you want reproducible, reviewable code. 2) Run the MCP server in an isolated environment (container/VM) because it launches a browser that can load arbitrary webpages and may expose session data. 3) The setup script uses shell execution (subprocess with shell=True) for static commands; review any changes before running and avoid modifying it to include user-provided input. 4) Disable telemetry and CrUX tracing as suggested if you will handle sensitive pages. 5) Verify the upstream repo/package maintainer and checksums if you require stronger supply-chain guarantees.

功能分析

Type: OpenClaw Skill Name: luke-chrome-devtools-mcp Version: 1.0.0 The skill bundle provides a standard integration for the Chrome DevTools MCP server, enabling browser automation capabilities like navigation, form filling, and screenshots. The included Python script (scripts/setup_chrome_mcp.py) handles environment verification and basic testing using standard system calls, and the SKILL.md documentation accurately reflects the tool's functionality without any signs of malicious instructions or data exfiltration.

能力评估

✓ Purpose & Capability

Name/description, SKILL.md, and the included Python helper all align: they install/run chrome-devtools-mcp via npx, check for Node/npx/Chrome, and provide an openclaw.json snippet. Requested resources (Node, Chrome) are appropriate for the stated purpose.

ℹ Instruction Scope

Runtime instructions and the setup script perform expected actions (run npx, check Chrome paths, read ~/.openclaw/openclaw.json for status). The script uses subprocess.run with shell=True for a few static commands — expected here but worth noting because shell execution can be sensitive if commands were constructed from untrusted input (they are static in this bundle).

ℹ Install Mechanism

No install spec is provided; SKILL.md and the script instruct use of npx -y chrome-devtools-mcp@latest. Using npx@latest will fetch and execute code from the npm registry at runtime — this is normal for Node tools but increases runtime exposure to remote code changes. Consider pinning a version or installing from a reviewed release if you need stronger guarantees.

✓ Credentials

The skill does not request any environment variables or secrets. It reads a local openclaw.json path (~/ .openclaw/openclaw.json) for status checks, which is appropriate for integration and is declared in the script output only.

✓ Persistence & Privilege

always is false and the skill is user-invocable. The bundle does not modify other skills or system-wide settings, and it does not persist credentials or write configuration files automatically — it only prints a suggested openclaw.json snippet.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install luke-chrome-devtools-mcp
安装完成后，直接呼叫该 Skill 的名称或使用 /luke-chrome-devtools-mcp 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of chrome-devtools-mcp: Google's official Chrome DevTools MCP server for browser automation and testing. - Enables control of Chrome via Puppeteer and DevTools Protocol: input automation, navigation, screenshots, performance tracing, network and console inspection. - Integrates with OpenClaw for AI agent workflows, including ready-to-use setup scripts and JSON configuration. - Provides a wide range of tools for UI automation, performance analysis, debugging, network inspection, device emulation, and advanced form handling. - Includes privacy options to disable usage and performance data sharing with Google.

元数据

Slug luke-chrome-devtools-mcp

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题