lighthouse-mcp
Lighthouse MCP 서버
웹 페이지의 다양한 성능 지표를 측정하는 데 도움이 되는 Google Lighthouse 도구를 탑재한 MCP 서버입니다.

특징
모든 URL에 대해 포괄적인 Lighthouse 감사를 실행합니다.
성과 점수 및 측정항목 가져오기
장치 에뮬레이션 구성(모바일/데스크톱)
네트워크 제한 제어
특정 감사 범주를 선택하세요
Related MCP server: LightScout MCP
설치
옵션 1: npx 사용(권장)
설치 없이 npx를 사용하여 도구를 직접 실행할 수 있습니다.
지엑스피1
옵션 2: 글로벌 설치
패키지를 전역으로 설치합니다.
npm install -g lighthouse-mcp그런 다음 실행합니다.
lighthouse-mcp옵션 3: 지역 개발
이 저장소를 복제하세요
종속성 설치:
npm install프로젝트를 빌드하세요:
npm run build서버를 실행합니다:
npm start
MCP 구성
npm(global 또는 npx)을 통해 설치한 경우
MCP 설정 구성 파일에 다음을 추가합니다.
{
"mcpServers": {
"lighthouse": {
"command": "npx",
"args": ["lighthouse-mcp"],
"disabled": false,
"autoApprove": []
}
}
}로컬 개발 버전을 사용하는 경우
MCP 설정 구성 파일에 다음을 추가합니다.
{
"mcpServers": {
"lighthouse": {
"command": "node",
"args": ["/absolute/path/to/lighthouse-mcp/build/index.js"],
"disabled": false,
"autoApprove": []
}
}
}/absolute/path/to/lighthouse-mcp 이 프로젝트의 실제 경로로 바꾸세요.
사용 가능한 도구
실행_감사
URL에 대한 포괄적인 Lighthouse 감사를 실행합니다.
매개변수:
url(필수): 감사할 URLcategories(선택 사항): 감사할 카테고리 배열(기본값은 모두)옵션: "성능", "접근성", "모범 사례", "seo", "pwa"
device(선택 사항): 에뮬레이션할 장치(기본값은 "모바일")옵션: "모바일", "데스크톱"
throttling(선택 사항): 네트워크 제한을 적용할지 여부(기본값은 true)
예:
{
"url": "https://example.com",
"categories": ["performance", "accessibility"],
"device": "desktop",
"throttling": false
}성과점수 얻기
URL에 대한 성능 점수만 받아보세요.
매개변수:
url(필수): 감사할 URLdevice(선택 사항): 에뮬레이션할 장치(기본값은 "모바일")옵션: "모바일", "데스크톱"
예:
{
"url": "https://example.com",
"device": "mobile"
}사용 예
MCP 서버가 구성되면 Claude와 함께 사용할 수 있습니다.
What's the performance score for example.com?클로드는 get_performance_score 도구를 사용하여 웹사이트를 분석하고 결과를 반환합니다.
요구 사항
노드.js 16+
Chrome/Chromium 브라우저(Lighthouse용)
추천서
Available Tools
2 toolsget_performance_scoreC
Get just the performance score for a URL
Inputs: url (required), device.
run_auditC
Run a Lighthouse audit on a URL
Inputs: url (required), device, categories, throttling.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
Both tools relate to Lighthouse audits, but they have distinct purposes: run_audit executes a full audit, while get_performance_score focuses on retrieving only the performance metric. However, get_performance_score is essentially a subset of run_audit, so an agent might be unsure when to use one over the other without additional context.
Both tool names follow a clear verb_noun pattern (run_audit, get_performance_score) with consistent snake_case and action-first style. The naming is predictable and unambiguous in structure.
With only 2 tools, the server feels under-scoped for a Lighthouse MCP. A typical Lighthouse workflow would expect a richer set of operations, such as fetching full report details, comparing scores, or handling multiple categories. The minimal count limits utility and feels thin.
The tool surface is severely incomplete for a Lighthouse server. It only covers running an audit and extracting the performance score, omitting other standard audit categories (accessibility, SEO, best practices) and report retrieval. Agents would hit dead ends if they need any other Lighthouse data.
Maintenance
Related MCP Connectors
Analyze web performance and get optimization insights from GTmetrix, directly in your AI workflow.
Run Google Lighthouse audits on any URL — performance, SEO, accessibility scores.
1Run SEO + AI-visibility (GEO) audits from Claude, Cursor & other AI clients.
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI models to perform Google Lighthouse website performance analysis, including Core Web Vitals, accessibility, SEO audits, and actionable optimization recommendations. Provides comprehensive web performance insights through natural language interactions.3,405 npm4MIT
- AlicenseAqualityDmaintenanceCore Web Vitals analysis powered by Lighthouse. Four tools: analyze a URL, compare two URLs, check against thresholds, or crawl an entire site. Works with Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool.464 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to control and inspect a live Chrome browser for automated web debugging, performance analysis, and Lighthouse audits. It allows agents to capture screenshots, monitor network requests, and measure Core Web Vitals using plain-English prompts.Apache 2.0
- AlicenseAqualityDmaintenanceConnects LLMs to Google PageSpeed Insights to analyze web performance, accessibility, SEO, and best practices, enabling AI assistants to audit and improve any web page.10MIT