agent-lighthouse

mcp
Security Audit
Warn
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 11 GitHub stars
Code Warn
  • fs module — File system access in action.yml
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Lighthouse-style audits for AI-agent readiness, LLM crawlers, MCP clients, and the agentic web

README.md

🗼 Agent Lighthouse

Lighthouse, but for AI agents.

Audit whether ChatGPT, Claude, Perplexity, MCP clients, AI crawlers, and agentic browsers can discover, parse, cite, and act on your website.

npm version npm downloads CI Docs License: Apache-2.0

Documentation · npm · Share a site score

Agent Lighthouse generated report preview


⚡ Quickstart

Run a zero-install scan directly in your terminal. The --view flag opens the standalone HTML report for screenshots, stakeholder review, and pull-request artifacts.

# 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 85

Agent Lighthouse checks 207 rules covering llms.txt, robots.txt crawler policy, Schema.org, OpenAPI discovery, WebMCP action surfaces, AEO/GEO content structure, accessibility, and technical readiness.


🎯 What Agent Lighthouse Checks

Agent Lighthouse evaluates websites across 10 audit categories grouped into 3 readiness pillars:

├── 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)

📦 Packages & Architecture

This repository is organized as a lightweight pnpm monorepo published under the @forkpoint scope:

Package npm Package Description
packages/cli @forkpoint/agent-lighthouse Main CLI binary (npx @forkpoint/agent-lighthouse <url>).
packages/core @forkpoint/agent-lighthouse-core Core gatherer-audit engine, scoring algorithms, and types.
packages/report @forkpoint/agent-lighthouse-report Standalone HTML, Markdown, and unified report view-model.
packages/mcp @forkpoint/agent-lighthouse-mcp Model Context Protocol (MCP) server for Claude / Cursor / IDEs.

🛡️ GitHub Actions CI

Use Agent Lighthouse as a pull-request gate for agentic readiness regressions:

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 }}

The action generates terminal, HTML, JSON, and Markdown reports. Set comment-on-pr: true with github-token to post the Markdown summary on pull requests. See the marketplace setup guide for release-ready examples.


💻 Programmatic Node.js / TypeScript SDK

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);

🤖 Model Context Protocol (MCP) Server

Add Agent Lighthouse to your Claude Desktop or Cursor IDE to let AI coding agents audit live staging URLs:

{
  "mcpServers": {
    "agent-lighthouse": {
      "command": "npx",
      "args": ["-y", "@forkpoint/agent-lighthouse-mcp"]
    }
  }
}

📣 Share Your Score

Generated reports are standalone files, so teams can attach them to pull requests, send them to clients, or publish before/after improvements.

[![Agent Lighthouse](https://img.shields.io/badge/Agent%20Lighthouse-ready-4f46e5)](https://github.com/ForkPoint/agent-lighthouse)

If you run Agent Lighthouse on a public site, share the result through the site score template. Good examples help other developers learn what agent-ready sites look like.

More launch material lives in:


🛠️ Development

# 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

📄 License

Apache-2.0 © ForkPoint

Reviews (0)

No results found