Agent Lighthouse MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agent Lighthouse MCP Serveraudit https://docs.example.com for AI agent readiness"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.

An example report. Its scores describe one past scan, not the site's current state.
โก Quickstart
Requires Node.js 22.22.2+ (22.x), 24.15.0+ (24.x), or 26+.
# Terminal report, plus HTML and JSON reports in ./reports
npx @forkpoint/agent-lighthouse https://example.com
# Open the HTML report in your browser
npx @forkpoint/agent-lighthouse https://example.com --view
# Fail (exit 1) below a score, for CI
npx @forkpoint/agent-lighthouse https://staging.example.com --min-score 85221 audits cover llms.txt, robots.txt crawler policy, Schema.org, OpenAPI discovery, WebMCP action surfaces, AEO/GEO content structure, agentic commerce, and operability. Every flag is in the CLI reference; config files and SDK options are in configuration; how the score is built is in scoring.
Related MCP server: maxaeo-ai-visibility-mcp
Agentic readiness skill
The agent-lighthouse skill lets a coding agent turn a report into verified fixes, on any website stack. It traces findings through source files and hosting settings, and keeps local fixes apart from deployed scan results.
Install it from this repository's marketplace. In Claude Code:
claude plugin marketplace add ForkPoint/agent-lighthouse
claude plugin install agent-lighthouse@agent-lighthouseIn Codex:
codex plugin marketplace add ForkPoint/agent-lighthouse
codex plugin add agent-lighthouse@agent-lighthouseFrom a local checkout, pass /absolute/path/to/agent-lighthouse to marketplace add. Start a new chat after installing. The CLI and MCP npm packages are separate. See the installation and workflow guide.
๐ฏ What Agent Lighthouse Checks
Agent Lighthouse evaluates websites across 8 agent-journey categories grouped into 3 readiness pillars:
โโโ 1. Agentic Readiness
โ โโโ Access & Crawl Control (robots.txt rules for GPTBot, ClaudeBot, PerplexityBot, blocks, status codes)
โ โโโ Machine Discovery (llms.txt, llms-full.txt, sitemaps, feeds, .well-known surfaces)
โ โโโ Agent Interfaces (WebMCP manifests, OpenAPI specs, agents.json, search actions)
โ โโโ Agentic Commerce (product offers, availability, checkout and payment surfaces)
โ
โโโ 2. AI Search Optimization
โ โโโ Content Extraction (clean main content, semantic structure, render and response cost)
โ โโโ Structured Data (Schema.org Product, Offer, SKU, GTIN, Organization, JSON-LD validity)
โ โโโ Answer Readiness (direct answerability, step lists, tables, unique data, citations)
โ
โโโ 3. Technical Foundation
โโโ Agent Operability & Safety (HTTPS, security.txt, tdmrep, stability, broken agent endpoints)๐ฆ Packages & Architecture
A pnpm monorepo published under the @forkpoint scope:
Package | npm Package | Description |
| Main CLI binary ( | |
| Core gatherer-audit engine, scoring algorithms, and types. | |
| Standalone HTML, Markdown, and unified report view-model. | |
| Model Context Protocol (MCP) server for Claude / Cursor / IDEs. |
๐ก๏ธ GitHub Actions CI
- uses: ForkPoint/agent-lighthouse@main
with:
url: https://staging.example.com
min-score: "85"
github-token: ${{ secrets.GITHUB_TOKEN }}The action writes terminal, HTML, JSON, and Markdown reports. With github-token it comments the Markdown summary on the pull request. Inputs and pinning are in the GitHub Action guide.
๐ป 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);
// overallScore is null when the scan saw too little to judge the site
console.log(`Overall Score: ${view.overallScore}/100 (${view.scoreTier})`);
const html = generateHtmlReport(report); // standalone HTML reportOptions are in programmatic options.
๐ค Model Context Protocol (MCP) Server
Let Claude Desktop, Cursor or another MCP client run scans through the audit_website tool:
{
"mcpServers": {
"agent-lighthouse": {
"command": "npx",
"args": ["-y", "@forkpoint/agent-lighthouse-mcp"]
}
}
}๐ฃ Share Your Score
Reports are standalone files: attach them to pull requests, send them to clients, or publish a before/after. Put the score in a README with a badge. Share a public site's result through the site score template.
More: media kit (boilerplate, screenshots, logos) ยท brand guide ยท brand kit download
๐ ๏ธ Development
git clone https://github.com/ForkPoint/agent-lighthouse.git
cd agent-lighthouse
pnpm install
pnpm build
pnpm test # deterministic tests with fixed inputsContributor rules, including how to add an audit, are in CLAUDE.md.
๐ License
Apache-2.0 ยฉ ForkPoint
This server cannot be deployed
Maintenance
Related MCP Connectors
Scan any public website and see how ready it is for AI agents and AI search, explained plainly.
Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.
Run full technical SEO audits of any website from your AI agent and get structured findings back.
Scan a website for AI search and agent readiness, then get a fix checklist for your agent.
Related MCP Servers
AlicenseAqualityAmaintenanceScans websites to evaluate agent-readiness and produce an ASO Score Report across 34 signals, helping improve discoverability, trust, and interoperability for AI agents.5440 npm1MIT- AlicenseAqualityBmaintenanceEnables 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.345 npm1MIT
- AlicenseAqualityAmaintenanceProvides AI-visibility scoring and site auditing capabilities for websites, enabling agents to check how sites appear in AI engines like ChatGPT and Perplexity, run full SEO/security audits, and monitor changes over time.15107 npm1MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to audit a website's AI visibility by checking crawler access, identity files, and page signals, and running a full scored audit across ChatGPT, Claude, Gemini, and Perplexity.1016 npmMIT