Agent Lighthouse MCP Server
⚡ Inicio rápido
Ejecuta un escaneo sin instalación directamente en tu terminal. La bandera --view abre el informe HTML independiente para capturas de pantalla, revisión de partes interesadas y artefactos de pull request.
# Instant audit (prints terminal report & generates HTML + JSON reports)
npx @forkpoint/agent-lighthouse https://yourstore.com
# Open the standalone HTML report in your browser
npx @forkpoint/agent-lighthouse https://yourstore.com --view
# Run in CI and fail if score is below threshold
npx @forkpoint/agent-lighthouse https://staging.yourstore.com --min-score 85Agent Lighthouse verifica 199 reglas que cubren llms.txt, política de rastreadores robots.txt, Schema.org, descubrimiento de OpenAPI, superficies de acción WebMCP, estructura de contenido AEO/GEO, accesibilidad y preparación técnica.
Related MCP server: Seonix SEO MCP
🎯 Lo que Agent Lighthouse verifica
Agent Lighthouse evalúa sitios web en 10 categorías de auditoría agrupadas en 3 pilares de preparación:
├── 1. Agentic Readiness
│ ├── AI Agent Tools & Action Surfaces (WebMCP manifests, OpenAPI specs, agents.json, ai-plugin.json)
│ ├── Content Discoverability (llms.txt, llms-full.txt, sitemaps, commerce links)
│ └── AI Crawler Permissions (robots.txt rules for GPTBot, ClaudeBot, PerplexityBot, etc.)
│
├── 2. AI Search Optimization
│ ├── Answer Engine Optimization (AEO) (direct answerability, step lists, table schemas)
│ └── Generative Engine Optimization (GEO) (unique data density, authoritative citations)
│
└── 3. Technical Foundation
├── Structured Data & Schema Markup (Schema.org Product, Offer, SKU, GTIN, Organization)
├── Meta Tags & AI Head Elements (AI content declarations, canonicals, Open Graph)
├── Semantic HTML & Content Structure (Headings hierarchy, landmarks, semantic tags)
├── Accessibility & Agent Interaction (Form labels, button roles, interactable elements)
└── Technical Readiness & Security (HTTPS, security.txt, TTFB response latency)📦 Paquetes y arquitectura
Este repositorio está organizado como un monorepositorio ligero de pnpm publicado bajo el ámbito @forkpoint:
Paquete | Paquete npm | Descripción |
| Binario principal de CLI ( | |
| Motor central de recopilación y auditoría, algoritmos de puntuación y tipos. | |
| Modelo de vista de informe unificado HTML, Markdown e independiente. | |
| Servidor del Protocolo de Contexto de Modelo (MCP) para Claude / Cursor / IDEs. |
🛡️ CI de GitHub Actions
Usa Agent Lighthouse como una puerta de pull request para regresiones de preparación agéntica:
name: Agent Lighthouse
on:
pull_request:
branches: [main]
jobs:
agent-lighthouse:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: ForkPoint/agent-lighthouse@main
with:
url: https://staging.yourstore.com
preset: ecommerce
min-score: "85"
github-token: ${{ secrets.GITHUB_TOKEN }}La acción genera informes en terminal, HTML, JSON y Markdown. Configura comment-on-pr: true con github-token para publicar el resumen en Markdown en los pull requests. Consulta la guía de configuración del marketplace para ejemplos listos para publicación.
💻 SDK programático de Node.js / TypeScript
import { runScan } from "@forkpoint/agent-lighthouse-core";
import {
buildReportView,
generateHtmlReport,
} from "@forkpoint/agent-lighthouse-report";
const report = await runScan("https://example.com");
const view = buildReportView(report);
console.log(`Overall Score: ${view.overallScore}/100 (${view.scoreTier})`);
// Generate standalone HTML report
const html = generateHtmlReport(report);🤖 Servidor del Protocolo de Contexto de Modelo (MCP)
Agrega Agent Lighthouse a tu Claude Desktop o Cursor IDE para permitir que los agentes de codificación de IA auditen URLs de staging en vivo:
{
"mcpServers": {
"agent-lighthouse": {
"command": "npx",
"args": ["-y", "@forkpoint/agent-lighthouse-mcp"]
}
}
}📣 Comparte tu puntuación
Los informes generados son archivos independientes, por lo que los equipos pueden adjuntarlos a pull requests, enviarlos a clientes o publicar mejoras de antes/después.
[](https://github.com/ForkPoint/agent-lighthouse)Si ejecutas Agent Lighthouse en un sitio público, comparte el resultado a través de la plantilla de puntuación del sitio. Los buenos ejemplos ayudan a otros desarrolladores a aprender cómo son los sitios preparados para agentes.
Más material de lanzamiento se encuentra en:
🛠️ Desarrollo
# Clone the repository
git clone https://github.com/ForkPoint/agent-lighthouse.git
cd agent-lighthouse
# Install dependencies
pnpm install
# Build all packages
pnpm build
# Run unit tests
pnpm test📄 Licencia
GPL-3.0-only © ForkPoint
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityBmaintenanceEnables AI agents to check whether AI assistants recommend a brand and audit a site's AI-agent readiness, providing visibility scores and specific gaps.MIT

Seonix SEO MCPofficial
AlicenseAqualityBmaintenanceLets any AI agent audit any website for SEO, GEO/AEO, and speed problems, reporting issues and recommendations without modifying the site.4MIT
ASO Score MCPofficial
AlicenseAqualityAmaintenanceScans websites to evaluate agent-readiness and produce an ASO Score Report across 34 signals, helping improve discoverability, trust, and interoperability for AI agents.534MIT- AlicenseAqualityAmaintenanceEnables AI agents to check whether a public website is crawlable, understandable, and ready for AI search workflows through local-only audits of robots.txt, sitemaps, metadata, and llms.txt.3511MIT
Related MCP Connectors
Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website.
SEO research, audits, backlinks, GSC, and content workflow tools for AI agents.
Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ForkPoint/agent-lighthouse'
If you have feedback or need assistance with the MCP directory API, please join our Discord server