Skip to main content
Glama
Playwright-Lighthouse MCP Server

Playwright-Lighthouse MCP Server

by kbyk004-diy

Servidor MCP de Dramaturgo-Lighthouse

Un servidor MCP que analiza el rendimiento de sitios web mediante Playwright y Lighthouse. Mediante el Protocolo de Contexto de Modelo (MCP), los LLM pueden realizar análisis de rendimiento de sitios web.

Características

  • Análisis de rendimiento con Lighthouse

  • Captura de pantalla

Related MCP server: Playwright MCP Server

Configuración

Prerrequisitos

  • Node.js 18 o superior

  • npm

Instalación

# Clone the repository
git clone https://github.com/kbyk004/playwright-lighthouse-mcp.git
cd playwright-lighthouse-mcp

# Install dependencies
npm install
npx playwright install

# Build
npm run build

Uso

Depuración del servidor MCP

npm run inspector

Integración con clientes MCP

Este servidor está diseñado para usarse con clientes compatibles con el Protocolo de Contexto de Modelo (MCP). Por ejemplo, se puede integrar con Claude for Desktop.

Ejemplo de configuración para Claude para escritorio

Agregue lo siguiente al archivo de configuración de Claude for Desktop ( ~/Library/Application Support/Claude/claude_desktop_config.json ):

{
  "mcpServers": {
    "playwright-lighthouse": {
      "command": "node",
      "args": [
        "/path-to/playwright-lighthouse-mcp/build/index.js"
      ]
    }
  }
}

Herramientas disponibles

1. faro de carrera

Ejecuta un análisis de rendimiento de Lighthouse en la página abierta actualmente.

Parámetros:

  • url : La URL del sitio web que desea analizar

  • categories : Matriz de categorías para analizar (predeterminado: ["rendimiento"])

    • Categorías disponibles: "rendimiento", "accesibilidad", "mejores prácticas", "seo", "pwa"

  • maxItems : Número máximo de elementos de mejora para mostrar en cada categoría (predeterminado: 3, máximo: 5)

2. tomar captura de pantalla

Toma una captura de pantalla de la página abierta actualmente.

Parámetros:

  • url : La URL del sitio web que desea capturar

  • fullPage : si es verdadero, captura una captura de pantalla de toda la página (predeterminado: falso)

Formato de salida

Los resultados del análisis incluyen:

  • Puntuaciones generales para cada categoría seleccionada con indicadores de color

  • Áreas clave de mejora agrupadas por categoría

  • Ruta al archivo de informe guardado

Licencia

Licencia MIT: consulte LICENCIA para obtener más detalles

Available Tools

2 tools
run-lighthouseC

Runs a Lighthouse performance analysis on the currently open page

Inputs: url (required), categories, maxItems.

take-screenshotC

Takes a screenshot of the currently open page

Inputs: url (required), fullPage.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one runs a performance analysis (run-lighthouse) and the other captures a visual snapshot (take-screenshot). There is no overlap in functionality, making it easy for an agent to select the correct tool based on the task.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (run-lighthouse, take-screenshot), using hyphenated lowercase names. This predictable naming scheme enhances readability and usability for agents.

    Tool Count2/5

    With only two tools, the server feels under-scoped for a Playwright-Lighthouse integration, which typically involves more operations like navigation, interaction, or detailed reporting. This limited set may hinder complex workflows that agents might expect from such a domain.

    Completeness2/5

    The tool surface is severely incomplete for browser automation and performance testing. Missing are essential operations like opening/closing pages, interacting with elements, running audits with specific configurations, or exporting results, which are core to the domain and could lead to agent failures in broader tasks.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
      19
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in real browser environments.
      31
      MIT
    • F
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or visually-tuned models.
      24
      -
    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages through structured accessibility snapshots without requiring screenshots or visually-tuned models.
      22
      Apache 2.0