Lighthouse MCP Server
@danielsogl
Lighthouse MCP Server について
MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"lighthouse-mcp-server": {
"command": "npx",
"args": [
"@danielsogl/lighthouse-mcp@latest",
"--chrome-path",
"/usr/bin/google-chrome"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Lighthouse MCP Server?
A Model Context Protocol (MCP) server that provides comprehensive web performance auditing and analysis using Google Lighthouse. It enables LLMs and AI agents to perform detailed website performance assessments, accessibility audits, SEO analysis, security checks, and Core Web Vitals monitoring.
How to use Lighthouse MCP Server?
Install via npx @danielsogl/lighthouse-mcp@latest and configure in your MCP client (VS Code, Cursor, Windsurf, Claude Desktop). For authenticated sessions, launch with a persistent Chrome profile using --profile-path and --no-headless. Attach to an existing Chrome instance using --chrome-port.
Key features of Lighthouse MCP Server
- Performance analysis with Core Web Vitals and optimization recommendations
- Accessibility audits with WCAG compliance checking
- SEO analysis and best practice recommendations
- Security assessment including HTTPS, CSP, and vulnerability scanning
- Resource analysis for JavaScript, CSS, images, and fonts
- Comparative mobile vs desktop analysis with throttling options
- Performance budgets with custom threshold monitoring
Use cases of Lighthouse MCP Server
- Automate Lighthouse audits for continuous performance monitoring
- Assess accessibility compliance and generate WCAG reports
- Analyze SEO opportunities and track best practices
- Compare performance across mobile and desktop devices
- Enforce performance budgets in CI/CD pipelines
FAQ from Lighthouse MCP Server
What are the runtime requirements?
Node.js 22.0.0 or newer and Chrome/Chromium (automatically managed by Lighthouse).
How do I use authenticated sessions with cookies and local storage?
Launch with a persistent Chrome profile using --profile-path <path> and --no-headless. Profile mode disables storage reset so sessions persist across audits.
Can I attach to an existing Chrome instance?
Yes, use --chrome-port <port> or --remote-debugging-port <port> to connect to a Chrome instance launched with remote debugging enabled. Pass --profile-path to preserve storage.
What tools are available for web analysis?
Tools include run_audit, get_performance_score, get_core_web_vitals, get_accessibility_score, get_seo_analysis, check_performance_budget, analyze_resources, find_unused_javascript, and get_security_audit.
Does the server support WSL2?
Yes, set the Chrome binary path explicitly via --chrome-path or the CHROME_PATH environment variable to select the correct Linux binary.
「その他」の他のコンテンツ
ICSS
chokcoco不止于 CSS
Awesome Mcp Servers
punkpeyeA collection of MCP servers.
Servers
modelcontextprotocolModel Context Protocol Servers
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
MCP Registry
modelcontextprotocolA community driven registry service for Model Context Protocol (MCP) servers.
コメント