Certificat AgentReady.md vérifié

Émis le 18 mai 2026, 09:36 sig: adc06a7767caa47d Vérifier →

URL analysée

https://www.agentport.dev/

Analyser une autre URL

Score AI-Ready

57 / D

Insuffisant

sur 100

Économie de tokens

Tokens HTML 41.747

Tokens Markdown 1530

Économie 96%

Détail du score

HTML sémantique 79/100

Efficacité du contenu 52/100

Visibilité IA 15/100

Données structurées 62/100

Accessibilité 100/100

Protocoles émergents

0 sur 3 détectés

Endpoints well-known recherchés par les agents IA. Détecté signifie qu’un agent peut découvrir et se connecter automatiquement à votre service.

OAuth Discovery RFC 8414
/.well-known/oauth-authorization-server
MCP Server Card Anthropic
/.well-known/mcp.json
A2A Agent Card Google
/.well-known/agent.json

Votre site n’a pas de fichier llms.txt. C’est le standard émergent pour aider les AI agents à comprendre la structure de votre site.

Comment implémenter

Créez un fichier /llms.txt en suivant la spécification de llmstxt.org. Incluez une description du site et des liens vers vos pages principales.

Votre page a un faible ratio de contenu réel par rapport au HTML total. Une grande partie du poids de la page est du balisage, des scripts ou des styles plutôt que du contenu.

Comment implémenter

Déplacez le CSS vers des feuilles de style externes, supprimez les styles en ligne, minimisez le JavaScript et assurez-vous que le HTML se concentre sur la structure du contenu.

Votre site ne supporte pas Markdown for Agents. Ce standard Cloudflare permet aux agents IA de demander du contenu en format markdown, réduisant l'utilisation de tokens de ~80%.

Comment implémenter

Implémentez un ou plusieurs : (1) Répondre à Accept: text/markdown avec du contenu markdown. (2) Servir des URLs .md (ex : /page.md). (3) Ajouter des balises <link rel="alternate" type="text/markdown">. (4) Ajouter des en-têtes HTTP Link pour la découverte markdown.

{\n res.setHeader('Vary', 'Accept');\n res.setHeader('Link', '; rel=\"alternate\"; type=\"text/markdown\"');\n if ((req.headers.accept || '').includes('text/markdown')) {\n res.type('text/markdown; charset=utf-8');\n return res.send(renderMarkdown('page'));\n }\n res.render('page');\n});"},{"id":"fastify","label":"Fastify","language":"javascript","filename":"server.js","code":"// Mechanisms 1 + 4: content negotiation + Link header\nfastify.get('/page', async (req, reply) => {\n reply.header('Vary', 'Accept');\n reply.header('Link', '; rel=\"alternate\"; type=\"text/markdown\"');\n if ((req.headers.accept || '').includes('text/markdown')) {\n return reply.type('text/markdown; charset=utf-8').send(renderMarkdown('page'));\n }\n return reply.view('/page.ejs');\n});"},{"id":"nextjs","label":"Next.js","language":"typescript","filename":"app/page/route.ts","code":"// Next.js App Router — Route Handler returning Markdown\nimport { NextRequest } from 'next/server';\nimport { renderMarkdown } from '@/lib/md';\nexport async function GET(req: NextRequest) {\n const accept = req.headers.get('accept') || '';\n if (accept.includes('text/markdown')) {\n return new Response(await renderMarkdown('page'), {\n headers: {\n 'Content-Type': 'text/markdown; charset=utf-8',\n 'Vary': 'Accept',\n },\n });\n }\n // Fall through to the page component\n return new Response(null, { status: 404 });\n}"},{"id":"wordpress","label":"WordPress","language":"php","filename":"functions.php","code":"post_content));\n exit;\n});"},{"id":"static","label":"Hugo / Jekyll / Astro","language":"txt","filename":"static/page.md","code":"# Mechanism 2: serve .md alongside .html\n# Hugo: place page.md in /static/ — built unchanged\n# Jekyll: drop page.md in /assets/ — copied as-is\n# Astro: src/pages/page.md.ts that exports a GET returning markdown\n\n# Then advertise with mechanism 3 in :\n# "}] }'>

Votre site n’a pas de fichier robots.txt. Ce fichier contrôle la manière dont les bots (y compris les AI agents) accèdent à votre site.

Comment implémenter

Créez un fichier /robots.txt qui autorise l’accès à vos pages de contenu. Incluez une directive Sitemap pointant vers votre sitemap.xml.

Aucun sitemap trouvé. Un sitemap aide les AI agents à découvrir toutes les pages de votre site.

Comment implémenter

Créez un /sitemap.xml listant toutes vos pages publiques. La plupart des CMS peuvent le générer automatiquement.

Aucune directive Content-Signal trouvée. Celles-ci indiquent aux agents IA comment ils peuvent utiliser votre contenu (indexation, entrée IA, données d'entraînement). L'emplacement recommandé est robots.txt.

Comment implémenter

Ajoutez Content-Signal à votre robots.txt : User-agent: *\nContent-Signal: search=yes, ai-input=yes, ai-train=no. Vous pouvez aussi l'ajouter comme en-tête HTTP sur les réponses markdown.

{\n res.setHeader('Content-Signal', 'search=yes, ai-input=yes, ai-train=no');\n next();\n});\n\n// Fastify\nfastify.addHook('onSend', (request, reply, payload, done) => {\n reply.header('Content-Signal', 'search=yes, ai-input=yes, ai-train=no');\n done();\n});"}] }'>

De nombreux éléments ont des attributs de style en ligne. Ils ajoutent du bruit pour les AI agents lors de l’extraction du contenu.

Comment implémenter

Déplacez tous les styles en ligne vers des classes CSS dans votre feuille de style. Utilisez des frameworks CSS utilitaires comme Tailwind si vous avez besoin de nombreux styles uniques.

Aucune donnée structurée Schema.org trouvée. JSON-LD aide les AI agents à extraire des informations factuelles et structurées de vos pages.

Comment implémenter

Ajoutez un bloc <script type="application/ld+json"> avec du balisage Schema.org. Utilisez les types appropriés : Article pour les billets de blog, Product pour les produits, Organization pour la page de votre entreprise.

Votre page repose fortement sur les éléments <div>. Les éléments sémantiques comme <section>, <nav>, <header>, <footer> et <aside> fournissent une structure significative pour les AI agents.

Comment implémenter

Remplacez les conteneurs <div> génériques par les éléments sémantiques appropriés. Utilisez <section> pour les groupes thématiques, <nav> pour la navigation, <header>/<footer> pour les en-têtes et pieds de page ou de section.

Balises Open Graph manquantes ou incomplètes. Les balises OG aident les AI agents (et les plateformes sociales) à comprendre le titre, la description et l’image de votre page.

Comment implémenter

Ajoutez les balises meta og:title, og:description et og:image dans le <head> de votre page.

post_content), 30);\n $image = get_the_post_thumbnail_url($post, 'large') ?: 'https://yoursite.com/og-image.jpg';\n $url = get_permalink($post);\n printf('' . \"\\n\", esc_attr($title));\n printf('' . \"\\n\", esc_attr($desc));\n printf('' . \"\\n\", esc_url($image));\n printf('' . \"\\n\", esc_url($url));\n echo '' . \"\\n\";\n}, 5);"},{"id":"nextjs","label":"Next.js","language":"typescript","filename":"app/page.tsx","code":"// Next.js App Router — Metadata API\nimport type { Metadata } from 'next';\n\nexport const metadata: Metadata = {\n title: \"AgentPort — MCP Infrastructure-as-a-Service\",\n description: \"Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.\",\n openGraph: {\n title: \"AgentPort — MCP Infrastructure-as-a-Service\",\n description: \"Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.\",\n url: \"https://www.agentport.dev/\",\n images: [\"https://yoursite.com/og-image.jpg\"],\n type: 'website',\n },\n};"}] }'>

Tokens Markdown: 1530

MCP Infrastructure-as-a-Service — Now in early access

## Your business.
Agent-native.
In 5 minutes.

Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.

SOC 2 compliant99.9% uptime SLAWorks with Claude & ChatGPTNo code changes neededFree tier available

## The web is being re-indexed. By AI agents.

- AI agents can't read your Shopify store
- ChatGPT can't add to cart for your customers
- Your products are invisible to Claude
- Browser AI skips right past your website

AgentPort

- Claude searches your catalog natively
- ChatGPT completes purchases in your store
- Google AI Mode recommends your listings
- Browser AI agents transact on your site

Projected 20260%

of product searches now start in AI chatbots, not Google.

Projected 20260

e-commerce transactions will be AI-agent initiated.

Projected 20260%

of websites have any MCP support today.

## Deploy in 4 steps. No engineers needed.

### Sign up & name your endpoint

Enter your business name. We derive your unique slug (e.g., 'Acme Shoes' → acme-shoes) and show you your future MCP endpoint: https://agentport.dev/api/acme-shoes/mcp

### Connect your data source

Choose from Shopify, Product Feed (CSV/JSON/XML), MongoDB, or Custom REST API. Paste your credentials. We handle the rest.

### Tools are auto-generated

AgentPort analyzes your connector capabilities and generates MCP tools — product search, inventory check, cart creation, checkout — with LLM-tested descriptions validated across Claude, GPT-4o, and Gemini.

### Go live on every AI platform

Copy your three integration artifacts — MCP endpoint, WebMCP script, UCP profile — and you’re live everywhere AI agents operate.

Making any website agent-ready

Agentport

.dev

WebMCP as a Service

🌐

WebMCP

Live

Browser-native agent tools via Chrome's WebMCP standard

📦

Product Feed MCP

Coming Soon

Structured catalog ingestion from any product feed or API

🛒

Checkout MCP

Coming Soon

Cart, shipping & order management for AI agents

💳

Payments MCP

Coming Soon

PCI-compliant payment flows via merchant's existing PSP

🧪

Agent Sim

Coming Soon

Test & simulate AI agent interactions before production

One integration → WebMCP + Backend MCP + UCP

agentport.dev

WebMCP

Browser Agents

Backend MCP

ChatGPT · Claude · Gemini

UCP

Google Commerce

## Connect anything. Auto-generate everything.

Pick a connector, supply your credentials, and AgentPort builds production-ready MCP tools automatically.

### Shopify

HTML sémantique

Utilise les éléments article ou main (100/100)

Has <main>

Hiérarchie de titres correcte (85/100)

1 heading level skip(s)

Utilise des éléments HTML sémantiques (16/100)

16 semantic elements, 310 divs (ratio: 5%)

Textes alternatifs descriptifs pour les images (100/100)

No images found

Faible profondeur d’imbrication des divs (100/100)

Avg div depth: 2.8, max: 6

Efficacité du contenu

Bon ratio de réduction de tokens (100/100)

96% token reduction (HTML→Markdown)

Bon ratio contenu/bruit (0/100)

Content ratio: 4.7% (5797 content chars / 124390 HTML bytes)

Styles en ligne minimaux (0/100)

149/1202 elements with inline styles (12.4%)

Poids de page raisonnable (80/100)

HTML size: 121KB

Visibilité IA

Possède un fichier llms.txt (0/100)

No llms.txt found

Possède un fichier robots.txt (0/100)

No robots.txt found

robots.txt autorise les bots IA (100/100)

No robots.txt — AI bots allowed by default

Possède un sitemap.xml (0/100)

No sitemap found

Support Markdown for Agents (0/100)

✗ Accept: text/markdown ✗ .md URL ✗ <link> tag ✗ Link header

A Content-Signal (robots.txt ou en-têtes HTTP) (0/100)

✓ robots.txt ✓ HTTP header ✗ Policy

Données structurées

Possède Schema.org / JSON-LD (0/100)

No JSON-LD / Schema.org found

Possède des balises Open Graph (67/100)

2/3 OG tags present

Possède une meta description (100/100)

Meta description: 161 chars

Possède une URL canonique (100/100)

Canonical URL present

Possède un attribut lang (100/100)

lang="en"

Accessibilité

Contenu disponible sans JavaScript (100/100)

Content available without JavaScript

Taille de page raisonnable (100/100)

Page size: 121KB

Le contenu apparaît tôt dans le HTML (100/100)

Main content starts at 2% of HTML

{
  "url": "https://www.agentport.dev/",
  "timestamp": 1779089767752,
  "fetch": {
    "mode": "simple",
    "timeMs": 602,
    "htmlSizeBytes": 124390,
    "supportsMarkdown": false,
    "markdownAgents": {
      "contentNegotiation": false,
      "mdUrl": {
        "found": false,
        "url": null
      },
      "linkTag": {
        "found": false,
        "url": null
      },
      "linkHeader": {
        "found": false,
        "url": null
      },
      "responseHeaders": {
        "contentSignal": null,
        "xMarkdownTokens": null,
        "vary": null
      },
      "frontmatter": {
        "present": false,
        "fields": [],
        "level": "none"
      },
      "level": "none"
    },
    "statusCode": 200
  },
  "extraction": {
    "title": "AgentPort — MCP Infrastructure-as-a-Service",
    "excerpt": "Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.",
    "byline": null,
    "siteName": "AgentPort",
    "lang": "en",
    "contentLength": 5797,
    "metadata": {
      "description": "Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.",
      "ogTitle": "AgentPort — MCP Infrastructure-as-a-Service",
      "ogDescription": "Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.",
      "ogImage": null,
      "ogType": "website",
      "canonical": "https://agentport.dev",
      "lang": "en",
      "schemas": [],
      "robotsMeta": null,
      "author": null,
      "generator": null,
      "markdownAlternateHref": null
    }
  },
  "markdown": "MCP Infrastructure-as-a-Service — Now in early access\n\n## Your business.\nAgent-native.\nIn 5 minutes.\n\nConvert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.\n\nSOC 2 compliant99.9% uptime SLAWorks with Claude & ChatGPTNo code changes neededFree tier available\n\n## The web is being re-indexed. By AI agents.\n\n-   AI agents can't read your Shopify store\n-   ChatGPT can't add to cart for your customers\n-   Your products are invisible to Claude\n-   Browser AI skips right past your website\n\nVS\n\nAgentPort\n\n-   Claude searches your catalog natively\n-   ChatGPT completes purchases in your store\n-   Google AI Mode recommends your listings\n-   Browser AI agents transact on your site\n\nProjected 20260%\n\nof product searches now start in AI chatbots, not Google.\n\nProjected 20260\n\ne-commerce transactions will be AI-agent initiated.\n\nProjected 20260%\n\nof websites have any MCP support today.\n\n## Deploy in 4 steps. No engineers needed.\n\n1\n\n### Sign up & name your endpoint\n\nEnter your business name. We derive your unique slug (e.g., 'Acme Shoes' → acme-shoes) and show you your future MCP endpoint: https://agentport.dev/api/acme-shoes/mcp\n\n2\n\n### Connect your data source\n\nChoose from Shopify, Product Feed (CSV/JSON/XML), MongoDB, or Custom REST API. Paste your credentials. We handle the rest.\n\n3\n\n### Tools are auto-generated\n\nAgentPort analyzes your connector capabilities and generates MCP tools — product search, inventory check, cart creation, checkout — with LLM-tested descriptions validated across Claude, GPT-4o, and Gemini.\n\n4\n\n### Go live on every AI platform\n\nCopy your three integration artifacts — MCP endpoint, WebMCP script, UCP profile — and you’re live everywhere AI agents operate.\n\nMaking any website agent-ready\n\nAgentport\n\n.dev\n\nWebMCP as a Service\n\n🌐\n\nWebMCP\n\nLive\n\nBrowser-native agent tools via Chrome's WebMCP standard\n\n📦\n\nProduct Feed MCP\n\nComing Soon\n\nStructured catalog ingestion from any product feed or API\n\n🛒\n\nCheckout MCP\n\nComing Soon\n\nCart, shipping & order management for AI agents\n\n💳\n\nPayments MCP\n\nComing Soon\n\nPCI-compliant payment flows via merchant's existing PSP\n\n🧪\n\nAgent Sim\n\nComing Soon\n\nTest & simulate AI agent interactions before production\n\nOne integration → WebMCP + Backend MCP + UCP\n\nagentport.dev\n\nWebMCP\n\nBrowser Agents\n\nBackend MCP\n\nChatGPT · Claude · Gemini\n\nUCP\n\nGoogle Commerce\n\n## Connect anything. Auto-generate everything.\n\nPick a connector, supply your credentials, and AgentPort builds production-ready MCP tools automatically.\n\n### Shopify\n\nMost Popular\n\nConnect your Shopify store with your Admin API token. AgentPort integrates with both the Admin REST API and Storefront GraphQL API.\n\nHighlight\n\nFull transactional — agents can actually complete purchases.\n\nAuto-generates\n\n6 tools (search, details, inventory, create cart, add to cart, checkout URL)\n\nSetup time2 minutes\n\nWooCommerce, Magento, BigCommerce, and Salesforce Commerce Cloud coming soon. [Join the waitlist](https://www.agentport.dev/#)\n\n## Production tools. Zero description writing.\n\nEvery auto-generated tool ships with LLM-optimized descriptions, strict input schemas, and anti-hallucination prompting.\n\nLLM-tested descriptions. All tool descriptions are validated for ≥90% correct first-attempt invocation on GPT-4o, Claude 3.5, and Gemini.\n\nAnti-hallucination prompting built in — agents are instructed not to assume filters the user never mentioned.\n\n## One setup. Every AI platform.\n\nOther tools give you one integration. AgentPort gives you three.\n\nNo other platform gives you all three. Most tools stop at one protocol and leave the rest of the AI web invisible to you.\n\nPOC · Live on AgentPort\n\n## Live proof: CribLiv, India's first AI-native rental marketplace\n\nCribLiv is a verified rental marketplace in Bangalore. Using AgentPort, they deployed six MCP tools that let AI agents search listings, compare properties, check availability, and book visits — without writing a single line of integration code.\n\n> “A tenant told Claude: ‘Find me a verified 2BHK in Koramangala under ₹25,000 with AC and parking.’ The agent called search\\_properties → get\\_property\\_details → compare\\_properties → schedule\\_visit. A visit was booked. Nothing else needed.”\n\n6\n\nMCP tools deployed\n\n0\n\nlines of code\n\n1\n\nWorking visit booking\n\n## Works everywhere agents live.\n\nClaude\n\nvia MCP Streamable HTTP\n\nClaude Desktop\n\nvia claude\\_desktop\\_config.json\n\nChatGPT\n\nvia OpenAI Responses API\n\nChrome AI\n\nvia WebMCP script tag\n\nGoogle AI Mode\n\nvia UCP submission\n\nGemini\n\nvia UCP profile\n\nCursor\n\nvia MCP\n\nWindsurf\n\nvia MCP\n\nAny MCP Client\n\nvia Streamable HTTP\n\nAgentPort uses the OpenAI Responses API — NOT the deprecated Assistants API (shutting down August 2026). Future-proof from day one.\n\n## A dashboard built for merchants, not engineers.\n\n4 screens from zero to live MCP endpoint. Business name, connector choice, review, deploy. Your endpoint is ready before you finish your coffee.\n\n1\n\nBusiness Info\n\n2\n\nConnector\n\n3\n\nReview\n\n4\n\nDeploy\n\nBusiness Name\n\nAcme Shoes\n\nIndustry\n\nE-commerce\n\nNext Step\n\n## Enterprise-grade infrastructure. Startup simplicity.\n\nAI Agent\n\nAgentPort MCP Server\n\nKernel Packages\n\nSupabase PostgreSQL\n\nExternal APIs\n\n## Simple pricing. Generous free tier.\n\nFREE\n\n### Explorer\n\n$0/month\n\nNo credit card\n\n-   1 tenant (1 business)\n-   1,000 tool calls / day\n-   Shopify + Feed connectors\n-   MCP endpoint\n-   WebMCP script\n-   UCP profile\n-   Community support\n\n[Start free →](https://www.agentport.dev/#)\n\nMOST POPULAR\n\nPRO\n\n### Builder\n\n$49/month\n\n-   3 tenants\n-   10,000 tool calls / day\n-   All connectors (incl. MongoDB + Custom API)\n-   Priority support\n-   Analytics dashboard\n-   Custom tool builder\n-   Visit requests (real estate)\n\n[Start 14-day trial →](https://www.agentport.dev/#)\n\nENTERPRISE\n\n### Scale\n\nCustom\n\n-   Unlimited tenants\n-   Unlimited tool calls\n-   Custom connectors\n-   Dedicated infrastructure\n-   SLA + uptime guarantee\n-   White-label option\n-   Dedicated support\n\n[Contact us →](https://www.agentport.dev/#)\n\nAll plans include MCP + WebMCP + UCP — three protocols, zero extra cost.\n\n## The AI agent economy is here. Is your business in it?\n\nMost websites are invisible to AI agents today. In 12 months, that's a 40% traffic problem. AgentPort fixes it in 5 minutes.\n\nJoin 200+ merchants on the early access waitlist.\n\n🔒 No spam. Magic link only. Cancel anytime.\n",
  "fullPageMarkdown": "AgentPort — MCP Infrastructure-as-a-Service\n\n🔌MCP Infrastructure-as-a-Service — Now in early access\n\n# Your business.\nAgent-native.\nIn 5 minutes.\n\nConvert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.\n\n[Get started free](https://www.agentport.dev/#)[Watch demo](https://www.agentport.dev/#)\n\nSOC 2 compliant99.9% uptime SLAWorks with Claude & ChatGPTNo code changes neededFree tier available\n\nterminal\n\n|\n\n## The web is being re-indexed. By AI agents.\n\n### Before AgentPort\n\n-   AI agents can't read your Shopify store\n-   ChatGPT can't add to cart for your customers\n-   Your products are invisible to Claude\n-   Browser AI skips right past your website\n\nVS\n\nAgentPort\n\n### After AgentPort\n\n-   Claude searches your catalog natively\n-   ChatGPT completes purchases in your store\n-   Google AI Mode recommends your listings\n-   Browser AI agents transact on your site\n\nProjected 20260%\n\nof product searches now start in AI chatbots, not Google.\n\nProjected 20260\n\ne-commerce transactions will be AI-agent initiated.\n\nProjected 20260%\n\nof websites have any MCP support today.\n\n## Deploy in 4 steps. No engineers needed.\n\n1\n\n### Sign up & name your endpoint\n\nEnter your business name. We derive your unique slug (e.g., 'Acme Shoes' → acme-shoes) and show you your future MCP endpoint: https://agentport.dev/api/acme-shoes/mcp\n\n2\n\n### Connect your data source\n\nChoose from Shopify, Product Feed (CSV/JSON/XML), MongoDB, or Custom REST API. Paste your credentials. We handle the rest.\n\n3\n\n### Tools are auto-generated\n\nAgentPort analyzes your connector capabilities and generates MCP tools — product search, inventory check, cart creation, checkout — with LLM-tested descriptions validated across Claude, GPT-4o, and Gemini.\n\n4\n\n### Go live on every AI platform\n\nCopy your three integration artifacts — MCP endpoint, WebMCP script, UCP profile — and you’re live everywhere AI agents operate.\n\nMaking any website agent-ready\n\nAgentport\n\n.dev\n\nWebMCP as a Service\n\n🌐\n\nWebMCP\n\nLive\n\nBrowser-native agent tools via Chrome's WebMCP standard\n\n📦\n\nProduct Feed MCP\n\nComing Soon\n\nStructured catalog ingestion from any product feed or API\n\n🛒\n\nCheckout MCP\n\nComing Soon\n\nCart, shipping & order management for AI agents\n\n💳\n\nPayments MCP\n\nComing Soon\n\nPCI-compliant payment flows via merchant's existing PSP\n\n🧪\n\nAgent Sim\n\nComing Soon\n\nTest & simulate AI agent interactions before production\n\nOne integration → WebMCP + Backend MCP + UCP\n\nagentport.dev\n\nWebMCP\n\nBrowser Agents\n\nBackend MCP\n\nChatGPT · Claude · Gemini\n\nUCP\n\nGoogle Commerce\n\n## Connect anything. Auto-generate everything.\n\nPick a connector, supply your credentials, and AgentPort builds production-ready MCP tools automatically.\n\nShopify\n\nMost Popular\n\nProduct Feed\n\nConnector\n\nCustom REST API\n\nConnector\n\nMongoDB\n\nBeta\n\nManual Tool Builder\n\nConnector\n\n### ShopifyMost Popular\n\nConnect your Shopify store with your Admin API token. AgentPort integrates with both the Admin REST API and Storefront GraphQL API.\n\nHighlight\n\nFull transactional — agents can actually complete purchases.\n\nAuto-generates\n\n6 tools (search, details, inventory, create cart, add to cart, checkout URL)\n\nSetup time2 minutes\n\nWooCommerce, Magento, BigCommerce, and Salesforce Commerce Cloud coming soon. [Join the waitlist](https://www.agentport.dev/#)\n\n## Production tools. Zero description writing.\n\nEvery auto-generated tool ships with LLM-optimized descriptions, strict input schemas, and anti-hallucination prompting.\n\nE-commerceReal Estate / Rentals\n\nmcp-tool-explorer\n\nE-commerce Tools (6)\n\nsearch\\_productsget\\_product\\_detailscheck\\_inventorycreate\\_cartwriteadd\\_to\\_cartwriteget\\_checkout\\_urlwrite\n\nRead-onlyTransactional\n\nMCP Tool DefinitionRead-only\n\n```\n{\n  \"name\": \"search_products\",\n  \"description\": \"Search catalog by keyword, category, price range. Call this before get_product_details.\",\n  \"inputSchema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"query\": {\n        \"type\": \"string\"\n      },\n      \"category\": {\n        \"type\": \"string\"\n      },\n      \"min_price\": {\n        \"type\": \"number\"\n      },\n      \"max_price\": {\n        \"type\": \"number\"\n      }\n    },\n    \"required\": [\n      \"query\"\n    ]\n  }\n}\n```\n\nLLM-tested descriptions. All tool descriptions are validated for ≥90% correct first-attempt invocation on GPT-4o, Claude 3.5, and Gemini.\n\nAnti-hallucination prompting built in — agents are instructed not to assume filters the user never mentioned.\n\n## One setup. Every AI platform.\n\nOther tools give you one integration. AgentPort gives you three.\n\nMCP Streamable HTTP Endpoint\n\n### For Claude, ChatGPT, and any MCP client\n\nYour personal MCP server, hosted and managed. Works with Claude Desktop, Claude.ai Projects, ChatGPT via OpenAI Responses API, and any MCP-compatible tool.\n\n// claude\\_desktop\\_config.json\n{\n  \"mcpServers\": {\n    \"acme-shoes\": {\n      \"url\": \"https://agentport.dev/api/acme-shoes/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ap\\_live\\_xxxx\"\n      }\n    }\n  }\n}\n\nClaudeChatGPTCursorMCP Clients\n\nAuthenticated endpoint. API key scoped per-client for full audit trail.\n\nWebMCP Browser Script\n\n### For Chrome browser AI (Chrome 146+)\n\nA single script tag makes your website's tools available to any browser AI agent. Zero authentication required.\n\n<!-- Add to your website's <head> -->\n<script\n  src=\"https://agentport.dev/api/acme-shoes/webmcp.js\"\n  defer\n></script>\n\nChrome AIWebMCP\n\nZero-auth public endpoint. Browser agents discover and call your tools directly.\n\nUniversal Context Profile (UCP)\n\n### For Google AI Mode & Gemini\n\nA structured machine-readable profile that Google's AI Mode and Gemini use to recommend your products.\n\n\\# Submit to Google Search Console\nGET https://agentport.dev/api/acme-shoes/ucp\n\n# Returns structured JSON profile:\n# - Business info\n# - Product catalog summary\n# - Available MCP tools\n# - Commerce capabilities\n\nGoogle AI ModeGemini\n\nGoogle AI Mode is already indexing UCP profiles.\n\nNo other platform gives you all three. Most tools stop at one protocol and leave the rest of the AI web invisible to you.\n\nPOC · Live on AgentPort\n\n## Live proof: CribLiv, India's first AI-native rental marketplace\n\nCribLiv is a verified rental marketplace in Bangalore. Using AgentPort, they deployed six MCP tools that let AI agents search listings, compare properties, check availability, and book visits — without writing a single line of integration code.\n\n> “A tenant told Claude: ‘Find me a verified 2BHK in Koramangala under ₹25,000 with AC and parking.’ The agent called search\\_properties → get\\_property\\_details → compare\\_properties → schedule\\_visit. A visit was booked. Nothing else needed.”\n\n6\n\nMCP tools deployed\n\n0\n\nlines of code\n\n1\n\nWorking visit booking\n\nClaude\n\n## Works everywhere agents live.\n\nClaude\n\nvia MCP Streamable HTTP\n\nClaude Desktop\n\nvia claude\\_desktop\\_config.json\n\nChatGPT\n\nvia OpenAI Responses API\n\nChrome AI\n\nvia WebMCP script tag\n\nGoogle AI Mode\n\nvia UCP submission\n\nGemini\n\nvia UCP profile\n\nCursor\n\nvia MCP\n\nWindsurf\n\nvia MCP\n\nAny MCP Client\n\nvia Streamable HTTP\n\nAgentPort uses the OpenAI Responses API — NOT the deprecated Assistants API (shutting down August 2026). Future-proof from day one.\n\n## A dashboard built for merchants, not engineers.\n\nOnboarding WizardTool ManagerConnector SetupIntegration HubAnalyticsVisit Requests\n\n### Onboarding Wizard\n\n4 screens from zero to live MCP endpoint. Business name, connector choice, review, deploy. Your endpoint is ready before you finish your coffee.\n\n1\n\nBusiness Info\n\n2\n\nConnector\n\n3\n\nReview\n\n4\n\nDeploy\n\nBusiness Name\n\nAcme Shoes\n\nIndustry\n\nE-commerce\n\nNext Step\n\n## Enterprise-grade infrastructure. Startup simplicity.\n\nAI Agent\n\nAgentPort MCP Server\n\nKernel Packages\n\nSupabase PostgreSQL\n\nExternal APIs\n\nShow architecture details\n\n## Simple pricing. Generous free tier.\n\nFREE\n\n### Explorer\n\n$0/month\n\nNo credit card\n\n-   1 tenant (1 business)\n-   1,000 tool calls / day\n-   Shopify + Feed connectors\n-   MCP endpoint\n-   WebMCP script\n-   UCP profile\n-   Community support\n\n[Start free →](https://www.agentport.dev/#)\n\nMOST POPULAR\n\nPRO\n\n### Builder\n\n$49/month\n\n-   3 tenants\n-   10,000 tool calls / day\n-   All connectors (incl. MongoDB + Custom API)\n-   Priority support\n-   Analytics dashboard\n-   Custom tool builder\n-   Visit requests (real estate)\n\n[Start 14-day trial →](https://www.agentport.dev/#)\n\nENTERPRISE\n\n### Scale\n\nCustom\n\n-   Unlimited tenants\n-   Unlimited tool calls\n-   Custom connectors\n-   Dedicated infrastructure\n-   SLA + uptime guarantee\n-   White-label option\n-   Dedicated support\n\n[Contact us →](https://www.agentport.dev/#)\n\nAll plans include MCP + WebMCP + UCP — three protocols, zero extra cost.\n\n## Frequently asked questions\n\nWhat is MCP and why does it matter?\n\nDo I need to know how to code?\n\nHow is AgentPort different from building my own MCP server?\n\nWhat about ChatGPT — I heard the Assistants API is deprecated?\n\nWhat is WebMCP and UCP?\n\nIs my data safe? Are my API credentials secure?\n\nCan I use this for non-ecommerce businesses?\n\nWhat happens when I hit my tool call limit?\n\n## The AI agent economy is here. Is your business in it?\n\nMost websites are invisible to AI agents today. In 12 months, that's a 40% traffic problem. AgentPort fixes it in 5 minutes.\n\nGet early access →\n\nJoin 200+ merchants on the early access waitlist.\n\n🔒 No spam. Magic link only. Cancel anytime.\n",
  "markdownStats": {
    "images": 0,
    "links": 4,
    "tables": 0,
    "codeBlocks": 0,
    "headings": 20
  },
  "tokens": {
    "htmlTokens": 41747,
    "markdownTokens": 1530,
    "reduction": 40217,
    "reductionPercent": 96
  },
  "score": {
    "score": 57,
    "grade": "D",
    "dimensions": {
      "semanticHtml": {
        "score": 79,
        "weight": 20,
        "grade": "B",
        "checks": {
          "uses_article_or_main": {
            "score": 100,
            "weight": 20,
            "details": "Has <main>"
          },
          "proper_heading_hierarchy": {
            "score": 85,
            "weight": 25,
            "details": "1 heading level skip(s)"
          },
          "semantic_elements": {
            "score": 16,
            "weight": 20,
            "details": "16 semantic elements, 310 divs (ratio: 5%)"
          },
          "meaningful_alt_texts": {
            "score": 100,
            "weight": 15,
            "details": "No images found"
          },
          "low_div_nesting": {
            "score": 100,
            "weight": 20,
            "details": "Avg div depth: 2.8, max: 6"
          }
        }
      },
      "contentEfficiency": {
        "score": 52,
        "weight": 25,
        "grade": "D",
        "checks": {
          "token_reduction_ratio": {
            "score": 100,
            "weight": 40,
            "details": "96% token reduction (HTML→Markdown)"
          },
          "content_to_noise_ratio": {
            "score": 0,
            "weight": 30,
            "details": "Content ratio: 4.7% (5797 content chars / 124390 HTML bytes)"
          },
          "minimal_inline_styles": {
            "score": 0,
            "weight": 15,
            "details": "149/1202 elements with inline styles (12.4%)"
          },
          "reasonable_page_weight": {
            "score": 80,
            "weight": 15,
            "details": "HTML size: 121KB"
          }
        }
      },
      "aiDiscoverability": {
        "score": 15,
        "weight": 25,
        "grade": "F",
        "checks": {
          "has_llms_txt": {
            "score": 0,
            "weight": 20,
            "details": "No llms.txt found"
          },
          "has_robots_txt": {
            "score": 0,
            "weight": 10,
            "details": "No robots.txt found"
          },
          "robots_allows_ai_bots": {
            "score": 100,
            "weight": 15,
            "details": "No robots.txt — AI bots allowed by default"
          },
          "has_sitemap": {
            "score": 0,
            "weight": 10,
            "details": "No sitemap found"
          },
          "supports_markdown_negotiation": {
            "score": 0,
            "weight": 25,
            "details": "No Markdown for Agents support detected"
          },
          "has_content_signals": {
            "score": 0,
            "weight": 20,
            "details": "No Content-Signal found (robots.txt or HTTP headers)"
          }
        }
      },
      "structuredData": {
        "score": 62,
        "weight": 15,
        "grade": "C",
        "checks": {
          "has_schema_org": {
            "score": 0,
            "weight": 30,
            "details": "No JSON-LD / Schema.org found"
          },
          "has_open_graph": {
            "score": 67,
            "weight": 25,
            "details": "2/3 OG tags present"
          },
          "has_meta_description": {
            "score": 100,
            "weight": 20,
            "details": "Meta description: 161 chars"
          },
          "has_canonical_url": {
            "score": 100,
            "weight": 15,
            "details": "Canonical URL present"
          },
          "has_lang_attribute": {
            "score": 100,
            "weight": 10,
            "details": "lang=\"en\""
          }
        }
      },
      "accessibility": {
        "score": 100,
        "weight": 15,
        "grade": "A",
        "checks": {
          "content_without_js": {
            "score": 100,
            "weight": 40,
            "details": "Content available without JavaScript"
          },
          "reasonable_page_size": {
            "score": 100,
            "weight": 30,
            "details": "Page size: 121KB"
          },
          "fast_content_position": {
            "score": 100,
            "weight": 30,
            "details": "Main content starts at 2% of HTML"
          }
        }
      }
    }
  },
  "recommendations": [
    {
      "id": "add_llms_txt",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_llms_txt.title",
      "descriptionKey": "rec.add_llms_txt.description",
      "howToKey": "rec.add_llms_txt.howto",
      "effort": "quick-win",
      "estimatedImpact": 10,
      "checkScore": 0,
      "checkDetails": "No llms.txt found"
    },
    {
      "id": "improve_content_ratio",
      "priority": "critical",
      "category": "contentEfficiency",
      "titleKey": "rec.improve_content_ratio.title",
      "descriptionKey": "rec.improve_content_ratio.description",
      "howToKey": "rec.improve_content_ratio.howto",
      "effort": "moderate",
      "estimatedImpact": 6,
      "checkScore": 0,
      "checkDetails": "Content ratio: 4.7% (5797 content chars / 124390 HTML bytes)"
    },
    {
      "id": "add_markdown_negotiation",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_markdown_negotiation.title",
      "descriptionKey": "rec.add_markdown_negotiation.description",
      "howToKey": "rec.add_markdown_negotiation.howto",
      "effort": "significant",
      "estimatedImpact": 6,
      "checkScore": 0,
      "checkDetails": "No Markdown for Agents support detected"
    },
    {
      "id": "add_robots_txt",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_robots_txt.title",
      "descriptionKey": "rec.add_robots_txt.description",
      "howToKey": "rec.add_robots_txt.howto",
      "effort": "quick-win",
      "estimatedImpact": 5,
      "checkScore": 0,
      "checkDetails": "No robots.txt found"
    },
    {
      "id": "add_sitemap",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_sitemap.title",
      "descriptionKey": "rec.add_sitemap.description",
      "howToKey": "rec.add_sitemap.howto",
      "effort": "quick-win",
      "estimatedImpact": 5,
      "checkScore": 0,
      "checkDetails": "No sitemap found"
    },
    {
      "id": "add_content_signals",
      "priority": "critical",
      "category": "aiDiscoverability",
      "titleKey": "rec.add_content_signals.title",
      "descriptionKey": "rec.add_content_signals.description",
      "howToKey": "rec.add_content_signals.howto",
      "effort": "quick-win",
      "estimatedImpact": 5,
      "checkScore": 0,
      "checkDetails": "No Content-Signal found (robots.txt or HTTP headers)"
    },
    {
      "id": "remove_inline_styles",
      "priority": "critical",
      "category": "contentEfficiency",
      "titleKey": "rec.remove_inline_styles.title",
      "descriptionKey": "rec.remove_inline_styles.description",
      "howToKey": "rec.remove_inline_styles.howto",
      "effort": "moderate",
      "estimatedImpact": 3,
      "checkScore": 0,
      "checkDetails": "149/1202 elements with inline styles (12.4%)"
    },
    {
      "id": "add_schema_org",
      "priority": "high",
      "category": "structuredData",
      "titleKey": "rec.add_schema_org.title",
      "descriptionKey": "rec.add_schema_org.description",
      "howToKey": "rec.add_schema_org.howto",
      "effort": "moderate",
      "estimatedImpact": 6,
      "checkScore": 0,
      "checkDetails": "No JSON-LD / Schema.org found"
    },
    {
      "id": "add_semantic_elements",
      "priority": "high",
      "category": "semanticHtml",
      "titleKey": "rec.add_semantic_elements.title",
      "descriptionKey": "rec.add_semantic_elements.description",
      "howToKey": "rec.add_semantic_elements.howto",
      "effort": "moderate",
      "estimatedImpact": 5,
      "checkScore": 16,
      "checkDetails": "16 semantic elements, 310 divs (ratio: 5%)"
    },
    {
      "id": "add_open_graph",
      "priority": "medium",
      "category": "structuredData",
      "titleKey": "rec.add_open_graph.title",
      "descriptionKey": "rec.add_open_graph.description",
      "howToKey": "rec.add_open_graph.howto",
      "effort": "quick-win",
      "estimatedImpact": 4,
      "checkScore": 67,
      "checkDetails": "2/3 OG tags present"
    }
  ],
  "llmsTxtPreview": "# AgentPort\n\n> Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.\n\n## Main\n- [AgentPort — MCP Infrastructure-as-a-Service](https://www.agentport.dev/): Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claud…\n\n",
  "llmsTxtExisting": null,
  "emergingProtocols": {
    "oauthDiscovery": {
      "exists": false,
      "url": "https://www.agentport.dev/.well-known/oauth-authorization-server"
    },
    "mcpServerCard": {
      "exists": false,
      "url": "https://www.agentport.dev/.well-known/mcp.json"
    },
    "a2aAgentCard": {
      "exists": false,
      "url": "https://www.agentport.dev/.well-known/agent.json"
    },
    "count": 0
  },
  "snippets": [
    {
      "id": "add_llms_txt",
      "title": "Create /llms.txt",
      "description": "Upload this file to your web root. It tells AI agents what your site is about and which pages matter.",
      "language": "markdown",
      "code": "# AgentPort\n\n> Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.\n\n## Main\n- [AgentPort — MCP Infrastructure-as-a-Service](https://www.agentport.dev/): Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claud…\n\n",
      "filename": "/llms.txt"
    },
    {
      "id": "add_open_graph",
      "title": "Add missing Open Graph tags",
      "description": "Open Graph tags control how your page looks when shared on social media and how AI platforms preview your URL in answers.",
      "language": "html",
      "code": "<meta property=\"og:image\" content=\"https://yoursite.com/og-image.jpg\">\n<meta property=\"og:url\" content=\"https://www.agentport.dev/\">\n<meta property=\"og:type\" content=\"website\">",
      "filename": "<head>",
      "stacks": [
        {
          "id": "html",
          "label": "HTML <head>",
          "language": "html",
          "filename": "<head>",
          "code": "<meta property=\"og:image\" content=\"https://yoursite.com/og-image.jpg\">\n<meta property=\"og:url\" content=\"https://www.agentport.dev/\">\n<meta property=\"og:type\" content=\"website\">"
        },
        {
          "id": "wordpress",
          "label": "WordPress",
          "language": "php",
          "filename": "functions.php",
          "code": "<?php\n// Quick Open Graph tags without a plugin (skip if Yoast / Rank Math is active)\nadd_action('wp_head', function () {\n    if (!is_singular()) return;\n    $post = get_queried_object();\n    $title = get_the_title($post);\n    $desc  = get_the_excerpt($post) ?: wp_trim_words(strip_tags($post->post_content), 30);\n    $image = get_the_post_thumbnail_url($post, 'large') ?: 'https://yoursite.com/og-image.jpg';\n    $url   = get_permalink($post);\n    printf('<meta property=\"og:title\" content=\"%s\">' . \"\\n\", esc_attr($title));\n    printf('<meta property=\"og:description\" content=\"%s\">' . \"\\n\", esc_attr($desc));\n    printf('<meta property=\"og:image\" content=\"%s\">' . \"\\n\", esc_url($image));\n    printf('<meta property=\"og:url\" content=\"%s\">' . \"\\n\", esc_url($url));\n    echo '<meta property=\"og:type\" content=\"article\">' . \"\\n\";\n}, 5);"
        },
        {
          "id": "nextjs",
          "label": "Next.js",
          "language": "typescript",
          "filename": "app/page.tsx",
          "code": "// Next.js App Router — Metadata API\nimport type { Metadata } from 'next';\n\nexport const metadata: Metadata = {\n  title: \"AgentPort — MCP Infrastructure-as-a-Service\",\n  description: \"Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.\",\n  openGraph: {\n    title: \"AgentPort — MCP Infrastructure-as-a-Service\",\n    description: \"Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes.\",\n    url: \"https://www.agentport.dev/\",\n    images: [\"https://yoursite.com/og-image.jpg\"],\n    type: 'website',\n  },\n};"
        }
      ]
    },
    {
      "id": "add_schema_org",
      "title": "Add Schema.org JSON-LD",
      "description": "Structured data helps AI agents understand the type, author, and purpose of your content.",
      "language": "html",
      "code": "<script type=\"application/ld+json\">\n{\n  \"@context\": \"https://schema.org\",\n  \"@type\": \"WebPage\",\n  \"name\": \"AgentPort — MCP Infrastructure-as-a-Service\",\n  \"description\": \"Convert your Shopify store, product catalog, or custom API into AI agent-ready MCP tools in 5 minutes. Works with Claude, ChatGPT, Chrome AI, and Google AI Mode.\",\n  \"url\": \"https://www.agentport.dev/\",\n  \"inLanguage\": \"en\",\n  \"isPartOf\": {\n    \"@type\": \"WebSite\",\n    \"name\": \"AgentPort\"\n  }\n}\n</script>",
      "filename": "<head>"
    },
    {
      "id": "add_robots_txt",
      "title": "Create /robots.txt",
      "description": "A robots.txt file tells crawlers (including AI bots) what they can and cannot access.",
      "language": "txt",
      "code": "User-agent: *\nAllow: /\n\nSitemap: https://www.agentport.dev/sitemap.xml",
      "filename": "/robots.txt"
    },
    {
      "id": "add_sitemap",
      "title": "Create /sitemap.xml",
      "description": "A sitemap helps AI agents discover all your pages. Most CMS platforms generate one automatically.",
      "language": "xml",
      "code": "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">\n  <url>\n    <loc>https://www.agentport.dev/</loc>\n    <lastmod>2026-05-18</lastmod>\n  </url>\n</urlset>",
      "filename": "/sitemap.xml"
    },
    {
      "id": "add_content_signals",
      "title": "Add Content-Signal directives",
      "description": "Content-Signal tells AI agents how they may use your content. The canonical location is robots.txt, but you can also expose it as an HTTP header from any stack.",
      "language": "txt",
      "code": "User-agent: *\nContent-Signal: search=yes, ai-input=yes, ai-train=no",
      "filename": "/robots.txt",
      "stacks": [
        {
          "id": "robots",
          "label": "robots.txt",
          "language": "txt",
          "filename": "/robots.txt",
          "code": "User-agent: *\nContent-Signal: search=yes, ai-input=yes, ai-train=no"
        },
        {
          "id": "nginx",
          "label": "Nginx",
          "language": "nginx",
          "filename": "server block",
          "code": "# Inside your server { } block:\nadd_header Content-Signal \"search=yes, ai-input=yes, ai-train=no\" always;"
        },
        {
          "id": "apache",
          "label": "Apache",
          "language": "apache",
          "filename": ".htaccess",
          "code": "# In .htaccess (or VirtualHost):\nHeader set Content-Signal \"search=yes, ai-input=yes, ai-train=no\""
        },
        {
          "id": "wordpress",
          "label": "WordPress",
          "language": "php",
          "filename": "functions.php",
          "code": "<?php\n// In your theme's functions.php or a small mu-plugin\nadd_action('send_headers', function () {\n    header('Content-Signal: search=yes, ai-input=yes, ai-train=no');\n});\n\n// Optional: also append the directive to the dynamic robots.txt\nadd_filter('robots_txt', function ($output) {\n    return $output . \"\\nContent-Signal: search=yes, ai-input=yes, ai-train=no\\n\";\n}, 10, 1);"
        },
        {
          "id": "nextjs",
          "label": "Next.js",
          "language": "typescript",
          "filename": "middleware.ts",
          "code": "// middleware.ts (Next.js 13+ App Router or Pages Router)\nimport { NextResponse } from 'next/server';\nexport function middleware() {\n  const res = NextResponse.next();\n  res.headers.set(\n    'Content-Signal',\n    'search=yes, ai-input=yes, ai-train=no'\n  );\n  return res;\n}\nexport const config = { matcher: '/:path*' };"
        },
        {
          "id": "cloudflare",
          "label": "Cloudflare Workers",
          "language": "javascript",
          "filename": "worker.js",
          "code": "// Cloudflare Worker that proxies your origin and adds the header\nexport default {\n  async fetch(request, env, ctx) {\n    const res = await fetch(request);\n    const newRes = new Response(res.body, res);\n    newRes.headers.set(\n      'Content-Signal',\n      'search=yes, ai-input=yes, ai-train=no'\n    );\n    return newRes;\n  },\n};"
        },
        {
          "id": "express",
          "label": "Express / Fastify",
          "language": "javascript",
          "filename": "server.js",
          "code": "// Express\napp.use((req, res, next) => {\n  res.setHeader('Content-Signal', 'search=yes, ai-input=yes, ai-train=no');\n  next();\n});\n\n// Fastify\nfastify.addHook('onSend', (request, reply, payload, done) => {\n  reply.header('Content-Signal', 'search=yes, ai-input=yes, ai-train=no');\n  done();\n});"
        }
      ]
    },
    {
      "id": "add_markdown_negotiation",
      "title": "Support Markdown for Agents",
      "description": "Let AI agents request a clean Markdown version of any page via content negotiation, .md alternate URLs, link tags or Link headers.",
      "language": "html",
      "code": "<!-- Mechanism 3: link tag advertising the .md alternate -->\n<link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">",
      "filename": "<head>",
      "stacks": [
        {
          "id": "html",
          "label": "HTML <head>",
          "language": "html",
          "filename": "<head>",
          "code": "<!-- Mechanism 3: link tag advertising the .md alternate -->\n<link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">"
        },
        {
          "id": "express",
          "label": "Express",
          "language": "javascript",
          "filename": "server.js",
          "code": "// Mechanisms 1 + 4: content negotiation + Link header\napp.get('/page', (req, res) => {\n  res.setHeader('Vary', 'Accept');\n  res.setHeader('Link', '</page.md>; rel=\"alternate\"; type=\"text/markdown\"');\n  if ((req.headers.accept || '').includes('text/markdown')) {\n    res.type('text/markdown; charset=utf-8');\n    return res.send(renderMarkdown('page'));\n  }\n  res.render('page');\n});"
        },
        {
          "id": "fastify",
          "label": "Fastify",
          "language": "javascript",
          "filename": "server.js",
          "code": "// Mechanisms 1 + 4: content negotiation + Link header\nfastify.get('/page', async (req, reply) => {\n  reply.header('Vary', 'Accept');\n  reply.header('Link', '</page.md>; rel=\"alternate\"; type=\"text/markdown\"');\n  if ((req.headers.accept || '').includes('text/markdown')) {\n    return reply.type('text/markdown; charset=utf-8').send(renderMarkdown('page'));\n  }\n  return reply.view('/page.ejs');\n});"
        },
        {
          "id": "nextjs",
          "label": "Next.js",
          "language": "typescript",
          "filename": "app/page/route.ts",
          "code": "// Next.js App Router — Route Handler returning Markdown\nimport { NextRequest } from 'next/server';\nimport { renderMarkdown } from '@/lib/md';\nexport async function GET(req: NextRequest) {\n  const accept = req.headers.get('accept') || '';\n  if (accept.includes('text/markdown')) {\n    return new Response(await renderMarkdown('page'), {\n      headers: {\n        'Content-Type': 'text/markdown; charset=utf-8',\n        'Vary': 'Accept',\n      },\n    });\n  }\n  // Fall through to the page component\n  return new Response(null, { status: 404 });\n}"
        },
        {
          "id": "wordpress",
          "label": "WordPress",
          "language": "php",
          "filename": "functions.php",
          "code": "<?php\n// Mechanism 1: respond to Accept: text/markdown on the same URL\nadd_action('template_redirect', function () {\n    if (!is_singular()) return;\n    $accept = $_SERVER['HTTP_ACCEPT'] ?? '';\n    if (strpos($accept, 'text/markdown') === false) return;\n    header('Content-Type: text/markdown; charset=utf-8');\n    header('Vary: Accept');\n    $post = get_queried_object();\n    echo \"# \" . get_the_title($post) . \"\\n\\n\";\n    echo wp_strip_all_tags(apply_filters('the_content', $post->post_content));\n    exit;\n});"
        },
        {
          "id": "static",
          "label": "Hugo / Jekyll / Astro",
          "language": "txt",
          "filename": "static/page.md",
          "code": "# Mechanism 2: serve .md alongside .html\n# Hugo: place page.md in /static/ — built unchanged\n# Jekyll: drop page.md in /assets/ — copied as-is\n# Astro: src/pages/page.md.ts that exports a GET returning markdown\n\n# Then advertise with mechanism 3 in <head>:\n#   <link rel=\"alternate\" type=\"text/markdown\" href=\"/page.md\">"
        }
      ]
    }
  ]
}

Utilisez notre API pour obtenir ceci de manière programmatique (bientôt disponible)

Ce JSON est à usage interne — contrairement au Markdown et au llms.txt, il n’est pas destiné à être téléversé sur votre site. Conservez-le comme référence pour suivre l’évolution de votre score, partagez-le avec votre équipe de développement ou intégrez-le dans votre pipeline CI/CD.

Partagez vos résultats

Twitter LinkedIn

Intégrez votre badge

Ajoutez ce badge à votre site. Il se met à jour automatiquement lorsque votre score de préparation à l’IA change.

Script Recommandé

<script src="https://agentready.md/badge.js" data-id="fa00dd1c-e68e-4842-bd48-af4e797a30b9" data-domain="www.agentport.dev"></script>

Markdown

[![AgentReady.md score for www.agentport.dev](https://agentready.md/badge/www.agentport.dev.svg)](https://agentready.md/fr/r/fa00dd1c-e68e-4842-bd48-af4e797a30b9)

Bientôt : Analyse de domaine complet

Explorez l’ensemble de votre domaine, générez un llms.txt et surveillez votre score de préparation IA dans le temps. Rejoignez la liste d’attente pour être informé.

✓ Vous êtes sur la liste ! Nous vous préviendrons lors du lancement.