← 返回 Skills 市场

Chrome Devtools Mcp 1.0.0

Name: Chrome Devtools Mcp 1.0.0
Author: sieyer

作者 Sieyer · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

505

总下载

当前安装

版本数

在 OpenClaw 中安装

/install chrome-devtools-mcp-1-0-0

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 to do what it says: it runs the chrome-devtools-mcp npm package to control Chrome. Before installing or enabling it: 1) Verify the npm package identity and maintainer (confirm it's the official ChromeDevTools package on npm/GitHub) rather than blindly running `npx ...@latest`. Prefer pinning to a known-good version if possible. 2) Be aware that npx will download and execute remote code each time (supply-chain risk). 3) Running the MCP server will control a browser instance — avoid using it with sessions that contain sensitive data or credentials, and use the provided flags to disable telemetry/performance CrUX. 4) The included Python script uses shell=True for some subprocess calls (currently with constant strings) — review it if you plan to modify or reuse it. 5) Note the minor metadata mismatch (ownerId) in the package files; this is not a functional blocker but warrants extra caution verifying the package provenance.

功能分析

Type: OpenClaw Skill Name: chrome-devtools-mcp-1-0-0 Version: 1.0.0 The skill is classified as suspicious due to the use of `shell=True` in `subprocess.run` within `scripts/setup_chrome_mcp.py`. While the commands executed are currently hardcoded and not directly exploitable by user input, this pattern introduces a significant shell injection vulnerability that could lead to remote code execution if the command string were ever constructed from untrusted sources. Additionally, the reliance on `npx -y chrome-devtools-mcp@latest` (mentioned in SKILL.md and used in the setup script) introduces a supply chain risk, as it downloads and executes code from npm, making the skill vulnerable to compromise of the upstream package.

能力评估

✓ Purpose & Capability

The skill name, description, SKILL.md, and included setup script all center on running the chrome-devtools-mcp npm package and controlling Chrome. Required system dependencies (Node.js, npx, Chrome/Chromium) are exactly what this capability needs. Note: _meta.json ownerId differs from the registry metadata ownerId provided in the header; this is a metadata inconsistency but does not change functional behavior.

ℹ Instruction Scope

SKILL.md and the setup/test script only instruct the agent to install/run the chrome-devtools-mcp package, check for Node/npx/Chrome, read openclaw.json (~/.openclaw/openclaw.json) for configuration, and start/stop the MCP server. These actions are within the expected scope. The script uses subprocess.run(..., shell=True) for some checks (constant commands only), which is acceptable here but worth reviewing since shell=True can be dangerous if later modified to include untrusted input.

ℹ Install Mechanism

This is an instruction-only skill (no install spec). The instructions rely on npx -y chrome-devtools-mcp@latest which fetches the package from the npm registry at runtime and uses the 'latest' tag (not pinned to a specific proven version). Fetching a remote npm package on demand is expected for this kind of skill but carries a supply-chain risk if the published package were compromised or if the maintainer changes the package unexpectedly.

✓ Credentials

The skill does not request environment variables, secrets, or extra credentials beyond needed local config checks. The script reads a local openclaw.json config path to detect MCP config, which is consistent with the advertised integration.

✓ Persistence & Privilege

always is false and model invocation is allowed (platform default). The skill does not request persistent system-wide privileges, does not modify other skills, and only suggests adding a server entry to the user's openclaw.json (user-controlled).

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 chrome-devtools-mcp-1-0-0
安装完成后，直接呼叫该 Skill 的名称或使用 /chrome-devtools-mcp-1-0-0 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 for browser automation and testing. - Control Chrome or Chromium via Puppeteer and the Chrome DevTools Protocol. - Automate input, navigation, screenshots, debugging, performance tracing, and device emulation. - 20+ tools to interact with pages: click, fill forms, handle dialogs, inspect network, analyze performance, and more. - Node.js v20.19+ and Chrome/Chromium required. - Includes OpenClaw integration instructions and common automation workflows. - Privacy controls for telemetry and performance data collection.

元数据

Slug chrome-devtools-mcp-1-0-0

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题