https://agent-ready.dev

{
  "url": "https://agent-ready.dev",
  "timestamp": 1781910430547,
  "fetch": {
    "mode": "simple",
    "timeMs": 851,
    "htmlSizeBytes": 274810,
    "supportsMarkdown": true,
    "markdownAgents": {
      "contentNegotiation": true,
      "mdUrl": {
        "found": true,
        "url": "https://agent-ready.dev/index.md"
      },
      "linkTag": {
        "found": true,
        "url": "https://agent-ready.dev/index.md"
      },
      "linkHeader": {
        "found": true,
        "url": "/index.md"
      },
      "responseHeaders": {
        "contentSignal": null,
        "xMarkdownTokens": null,
        "vary": null
      },
      "frontmatter": {
        "present": false,
        "fields": [],
        "level": "none"
      },
      "level": "application"
    },
    "statusCode": 200
  },
  "extraction": {
    "title": "Agent Ready — AI Agent Readability Checker",
    "excerpt": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard.",
    "byline": null,
    "siteName": "Agent Ready",
    "lang": "en",
    "contentLength": 3190,
    "metadata": {
      "description": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly.",
      "ogTitle": "Agent Ready — AI Agent Readability Checker",
      "ogDescription": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard.",
      "ogImage": "https://agent-ready.dev/opengraph-image?5d6d2cbe1dca6db1",
      "ogType": "website",
      "canonical": "https://agent-ready.dev",
      "lang": "en",
      "schemas": [
        {
          "@type": "Organization",
          "@id": "https://agent-ready.dev/#organization",
          "name": "Agent Ready",
          "url": "https://agent-ready.dev",
          "description": "AI agent readability scanner. Scores any website against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests, returning a 0–100 score with per-check fixes.",
          "logo": "https://agent-ready.dev/opengraph-image",
          "sameAs": [
            "https://www.wikidata.org/wiki/Q139962352",
            "https://www.wikidata.org/wiki/Q139962407",
            "https://github.com/mlava/agent-ready-cli",
            "https://github.com/mlava/agent-ready-skills",
            "https://github.com/mlava/agent-ready-cursor-plugin",
            "https://github.com/mlava/agent-ready-mcp",
            "https://github.com/mlava/agent-ready-gemini",
            "https://github.com/mlava/agent-ready-sdk"
          ],
          "contactPoint": [
            {
              "@type": "ContactPoint",
              "contactType": "customer support",
              "email": "[email protected]",
              "url": "https://agent-ready.dev/about"
            },
            {
              "@type": "ContactPoint",
              "contactType": "abuse",
              "email": "[email protected]"
            },
            {
              "@type": "ContactPoint",
              "contactType": "privacy",
              "email": "[email protected]"
            }
          ]
        },
        {
          "@type": "WebSite",
          "@id": "https://agent-ready.dev/#website",
          "url": "https://agent-ready.dev",
          "name": "Agent Ready",
          "description": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard.",
          "publisher": {
            "@id": "https://agent-ready.dev/#organization"
          },
          "inLanguage": "en-GB",
          "dateModified": "2026-06-12",
          "potentialAction": {
            "@type": "SearchAction",
            "target": {
              "@type": "EntryPoint",
              "urlTemplate": "https://agent-ready.dev/ask?query={search_term_string}"
            },
            "query-input": "required name=search_term_string"
          }
        },
        {
          "@type": "Service",
          "@id": "https://agent-ready.dev/#service",
          "name": "Agent Ready",
          "url": "https://agent-ready.dev",
          "description": "AI agent readability scanner. Runs 69 checks against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol specs (MCP, A2A, agents.json, agent-permissions.json), returning a 0–100 score and per-check fix guidance.",
          "serviceType": "Agent readability scanner",
          "provider": {
            "@id": "https://agent-ready.dev/#organization"
          },
          "areaServed": "Worldwide",
          "audience": {
            "@type": "Audience",
            "audienceType": "Developers"
          },
          "offers": [
            {
              "@type": "Offer",
              "name": "Free",
              "price": "0",
              "priceCurrency": "USD",
              "url": "https://agent-ready.dev/pricing"
            },
            {
              "@type": "Offer",
              "name": "Pro",
              "priceCurrency": "USD",
              "priceSpecification": {
                "@type": "UnitPriceSpecification",
                "price": "19",
                "priceCurrency": "USD",
                "unitText": "MONTH"
              },
              "url": "https://agent-ready.dev/pricing"
            }
          ]
        },
        {
          "@context": "https://schema.org",
          "@type": "WebApplication",
          "name": "Agent Ready",
          "url": "https://agent-ready.dev",
          "description": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly.",
          "applicationCategory": "DeveloperApplication",
          "operatingSystem": "Web",
          "publisher": {
            "@id": "https://agent-ready.dev/#organization"
          },
          "dateModified": "2026-06-12",
          "softwareHelp": {
            "@type": "CreativeWork",
            "url": "https://agent-ready.dev/docs"
          },
          "offers": {
            "@type": "AggregateOffer",
            "priceCurrency": "USD",
            "lowPrice": "0",
            "highPrice": "19",
            "offerCount": "2"
          }
        },
        {
          "@context": "https://schema.org",
          "@type": "WebPage",
          "name": "Agent Ready — AI agent readability checker",
          "url": "https://agent-ready.dev",
          "description": "Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your site AI-agent friendly.",
          "inLanguage": "en-GB",
          "author": {
            "@id": "https://agent-ready.dev/#organization"
          },
          "datePublished": "2026-04-16",
          "dateModified": "2026-06-12",
          "speakable": {
            "@type": "SpeakableSpecification",
            "cssSelector": [
              "#speakable-headline",
              "#speakable-summary"
            ]
          },
          "isPartOf": {
            "@id": "https://agent-ready.dev/#website"
          },
          "publisher": {
            "@id": "https://agent-ready.dev/#organization"
          }
        },
        {
          "@context": "https://schema.org",
          "@type": "BreadcrumbList",
          "itemListElement": [
            {
              "@type": "ListItem",
              "position": 1,
              "name": "Home",
              "item": "https://agent-ready.dev"
            }
          ]
        },
        {
          "@context": "https://schema.org",
          "@type": "FAQPage",
          "name": "Agent readability — frequently asked questions",
          "url": "https://agent-ready.dev",
          "description": "Common questions about AI agent readability: what it is, why it matters for SEO, what the scanner checks, and how the 0–100 score is calculated.",
          "mainEntity": [
            {
              "@type": "Question",
              "name": "What is agent readability?",
              "acceptedAnswer": {
                "@type": "Answer",
                "text": "Agent readability is how easily AI agents — ChatGPT, Claude, Perplexity, Google Gemini, coding assistants, MCP clients — can discover, parse, and act on a website. It spans three surfaces: discovery files (llms.txt, robots.txt, sitemaps), structural signals (semantic headings, canonical links, structured data, markdown mirrors), and protocol manifests (MCP Server Cards, A2A Agent Cards, agents.json, agent-permissions.json)."
              }
            },
            {
              "@type": "Question",
              "name": "Why does AI agent readability matter for SEO?",
              "acceptedAnswer": {
                "@type": "Answer",
                "text": "AI agents crawl what loads cleanly and cite what parses correctly. Sites that score well get summarised accurately and referred qualified traffic; sites that score poorly get paraphrased badly or skipped entirely. Unlike traditional SEO, you do not need to rank on page 1 — structured, citable content gets pulled even when organic rank is low."
              }
            },
            {
              "@type": "Question",
              "name": "What does the agent readability scanner check?",
              "acceptedAnswer": {
                "@type": "Answer",
                "text": "Agent Ready runs 69 checks across four families: 38 against the Vercel Agent Readability Spec (15 site-wide plus 23 per-page covering meta tags, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS rendering), 10 against the llmstxt.org specification, 20 against agent protocols (MCP Server Cards, A2A Agent Cards, Wildcard agents.json, agent-permissions.json, UCP, x402, NLWeb, API Catalog, Web Bot Auth, Agent Skills Discovery, agent-driven UI / A2UI, MPP machine payments, AP2 (Agent Payments Protocol), and ACP (Agentic Commerce Protocol)), and 1 content-integrity check (browser-vs-AI-crawler cloaking detection)."
              }
            },
            {
              "@type": "Question",
              "name": "How is the agent readability score calculated?",
              "acceptedAnswer": {
                "@type": "Answer",
                "text": "Score = round((passed checks / total checks) × 100). The denominator compounds: 15 site-wide plus (23 per-page × number of pages scanned). A systemic issue like a missing canonical link on every page compounds significantly. Ratings: 90-100 Excellent, 70-89 Good, 50-69 Fair, 0-49 Needs Improvement."
              }
            }
          ]
        }
      ],
      "robotsMeta": null,
      "author": null,
      "generator": null,
      "markdownAlternateHref": "https://agent-ready.dev/index.md"
    }
  },
  "markdown": "## What is agent readability?\n\nAgent readability is how easily AI agents — ChatGPT, Claude, Perplexity, Google Gemini, coding assistants, MCP clients — can discover, parse, and act on a website. It spans three surfaces: discovery files (`llms.txt`, `robots.txt`, sitemaps), structural signals (semantic headings, canonical links, structured data, markdown mirrors), and protocol manifests (MCP Server Cards, A2A Agent Cards, agents.json, agent-permissions.json).\n\n## Why does AI agent readability matter for SEO?\n\nAI agents crawl what loads cleanly and cite what parses correctly. The incentives are sharp: a [July 2025 Pew Research study](https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/) found users who encounter a Google AI Overview click on a source link only about 8% of the time — roughly half the rate of searches without an AI summary. Princeton’s [GEO study (KDD 2024)](https://arxiv.org/abs/2311.09735) measured that adding source citations to a page lifted its inclusion in AI answers by roughly 40%, with statistics and quotations close behind. Sites that score well get summarised accurately and referred qualified traffic; sites that score poorly get paraphrased (badly) or skipped entirely. Unlike traditional SEO, you don’t need to rank on page 1 — structured, citable content gets pulled even when organic rank is low.\n\n## What does the agent readability scanner check?\n\n-   **Vercel Agent Readability Spec** — 15 site-wide checks (llms.txt, robots.txt, sitemap.xml, sitemap.md, AGENTS.md, HTTPS, OpenAPI) plus 23 per-page checks (meta tags, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS-rendering dependency).\n-   **llmstxt.org** — 10 checks against the llms.txt format (H1 present, blockquote summary, H2 sections, link format, content-type, llms-full.txt).\n-   **Agent protocols** — 15 checks covering MCP Server Cards (SEP-1649 / [RFC 9728](https://datatracker.ietf.org/doc/html/rfc9728) OAuth Protected Resource metadata), A2A Agent Cards (a2a.proto v1.0.0), Wildcard agents.json, agent-permissions.json, UCP (Universal Commerce Protocol), x402 (HTTP 402 Payment Required), and NLWeb (natural-language /ask endpoint).\n\n## How is the agent readability score calculated?\n\n`score = round((passed checks / total checks) × 100)`. The denominator compounds: 15 site-wide + (23 per-page × number of pages scanned). A systemic issue like a missing canonical link on every page compounds significantly. Ratings: 90-100 Excellent, 70-89 Good, 50-69 Fair, 0-49 Needs Improvement.\n\n## Why choose Agent Ready over an SEO scanner or manual audit?\n\nAgent Ready is built specifically for AI-agent readability — not a human-search SEO tool with an “AI” tab bolted on. It is the only scanner that validates llms.txt, the full Vercel Agent Readability Spec, *and* every agent-protocol manifest (MCP, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb) in a single pass.\n\n-   **vs general SEO crawlers** (Lighthouse, Screaming Frog) — they optimise pages for human search engines and never check the agent-protocol surfaces AI agents read.\n-   **vs manual audits** — all 69 checks run in seconds, every deploy, instead of hand-verifying five specs by hand.\n-   **vs single-spec llms.txt validators** — those lint one file; Agent Ready covers the other ~50 conditions too, with a plain-English fix for each failure.\n\nSee the full breakdown: [Agent Ready vs the alternatives](https://agent-ready.dev/agent-ready-vs-alternatives).\n",
  "fullPageMarkdown": "Agent Ready — AI Agent Readability Checker\n\n[Agent Readyagent.ready](https://agent-ready.dev/)\n\nNo sign-up required — scan instantly\n\n# Is your site ready for AI agents?\n\nScore any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes in seconds.\n\nScan\n\nLast updated 2026-06-12\n\n[\n\n## Readability spec\n\n15 site-wide + 23 per-page checks from the Vercel Agent Readability Spec\n\n](https://agent-ready.dev/agent-readability-score)[\n\n## llms.txt\n\n10 checks against the llmstxt.org specification for LLM-friendly content\n\n](https://agent-ready.dev/llms-txt-checker)[\n\n## Agent protocols\n\n15 checks covering MCP, A2A, agents.json, UCP, x402, NLWeb, API Catalog, Web Bot Auth, and Agent Skills Discovery\n\n](https://agent-ready.dev/mcp-card-validator)\n\n## Fix guidance\n\nEvery failing check includes a clear, actionable how-to-fix explanation\n\nBuilding with Agent Ready? [Developer documentation](https://agent-ready.dev/docs) — REST API, MCP server, OpenAPI spec, and installable skills.\n\n## What is agent readability?\n\nAgent readability is how easily AI agents — ChatGPT, Claude, Perplexity, Google Gemini, coding assistants, MCP clients — can discover, parse, and act on a website. It spans three surfaces: discovery files (`llms.txt`, `robots.txt`, sitemaps), structural signals (semantic headings, canonical links, structured data, markdown mirrors), and protocol manifests (MCP Server Cards, A2A Agent Cards, agents.json, agent-permissions.json).\n\n## Why does AI agent readability matter for SEO?\n\nAI agents crawl what loads cleanly and cite what parses correctly. The incentives are sharp: a [July 2025 Pew Research study](https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/) found users who encounter a Google AI Overview click on a source link only about 8% of the time — roughly half the rate of searches without an AI summary. Princeton’s [GEO study (KDD 2024)](https://arxiv.org/abs/2311.09735) measured that adding source citations to a page lifted its inclusion in AI answers by roughly 40%, with statistics and quotations close behind. Sites that score well get summarised accurately and referred qualified traffic; sites that score poorly get paraphrased (badly) or skipped entirely. Unlike traditional SEO, you don’t need to rank on page 1 — structured, citable content gets pulled even when organic rank is low.\n\n## What does the agent readability scanner check?\n\n-   **Vercel Agent Readability Spec** — 15 site-wide checks (llms.txt, robots.txt, sitemap.xml, sitemap.md, AGENTS.md, HTTPS, OpenAPI) plus 23 per-page checks (meta tags, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS-rendering dependency).\n-   **llmstxt.org** — 10 checks against the llms.txt format (H1 present, blockquote summary, H2 sections, link format, content-type, llms-full.txt).\n-   **Agent protocols** — 15 checks covering MCP Server Cards (SEP-1649 / [RFC 9728](https://datatracker.ietf.org/doc/html/rfc9728) OAuth Protected Resource metadata), A2A Agent Cards (a2a.proto v1.0.0), Wildcard agents.json, agent-permissions.json, UCP (Universal Commerce Protocol), x402 (HTTP 402 Payment Required), and NLWeb (natural-language /ask endpoint).\n\n## How is the agent readability score calculated?\n\n`score = round((passed checks / total checks) × 100)`. The denominator compounds: 15 site-wide + (23 per-page × number of pages scanned). A systemic issue like a missing canonical link on every page compounds significantly. Ratings: 90-100 Excellent, 70-89 Good, 50-69 Fair, 0-49 Needs Improvement.\n\n## Why choose Agent Ready over an SEO scanner or manual audit?\n\nAgent Ready is built specifically for AI-agent readability — not a human-search SEO tool with an “AI” tab bolted on. It is the only scanner that validates llms.txt, the full Vercel Agent Readability Spec, *and* every agent-protocol manifest (MCP, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb) in a single pass.\n\n-   **vs general SEO crawlers** (Lighthouse, Screaming Frog) — they optimise pages for human search engines and never check the agent-protocol surfaces AI agents read.\n-   **vs manual audits** — all 69 checks run in seconds, every deploy, instead of hand-verifying five specs by hand.\n-   **vs single-spec llms.txt validators** — those lint one file; Agent Ready covers the other ~50 conditions too, with a plain-English fix for each failure.\n\nSee the full breakdown: [Agent Ready vs the alternatives](https://agent-ready.dev/agent-ready-vs-alternatives).\n",
  "markdownStats": {
    "images": 0,
    "links": 4,
    "tables": 0,
    "codeBlocks": 0,
    "headings": 5
  },
  "tokens": {
    "htmlTokens": 85594,
    "markdownTokens": 862,
    "reduction": 84732,
    "reductionPercent": 99
  },
  "score": {
    "score": 85,
    "grade": "B",
    "dimensions": {
      "semanticHtml": {
        "score": 91,
        "weight": 20,
        "grade": "A",
        "checks": {
          "uses_article_or_main": {
            "score": 100,
            "weight": 20,
            "details": "Has <main>"
          },
          "proper_heading_hierarchy": {
            "score": 100,
            "weight": 25,
            "details": "Clean heading hierarchy"
          },
          "semantic_elements": {
            "score": 56,
            "weight": 20,
            "details": "7 semantic elements, 35 divs (ratio: 17%)"
          },
          "meaningful_alt_texts": {
            "score": 100,
            "weight": 15,
            "details": "1/1 images with meaningful alt text"
          },
          "low_div_nesting": {
            "score": 100,
            "weight": 20,
            "details": "Avg div depth: 1.6, max: 4"
          }
        }
      },
      "contentEfficiency": {
        "score": 63,
        "weight": 25,
        "grade": "C",
        "checks": {
          "token_reduction_ratio": {
            "score": 100,
            "weight": 40,
            "details": "99% token reduction (HTML→Markdown)"
          },
          "content_to_noise_ratio": {
            "score": 0,
            "weight": 30,
            "details": "Content ratio: 1.2% (3190 content chars / 274810 HTML bytes)"
          },
          "minimal_inline_styles": {
            "score": 100,
            "weight": 15,
            "details": "0/360 elements with inline styles (0.0%)"
          },
          "reasonable_page_weight": {
            "score": 50,
            "weight": 15,
            "details": "HTML size: 268KB"
          }
        }
      },
      "aiDiscoverability": {
        "score": 92,
        "weight": 25,
        "grade": "A",
        "checks": {
          "has_llms_txt": {
            "score": 100,
            "weight": 20,
            "details": "llms.txt exists and is valid"
          },
          "has_robots_txt": {
            "score": 100,
            "weight": 10,
            "details": "robots.txt exists"
          },
          "robots_allows_ai_bots": {
            "score": 100,
            "weight": 15,
            "details": "All major AI bots allowed"
          },
          "has_sitemap": {
            "score": 100,
            "weight": 10,
            "details": "Sitemap found"
          },
          "supports_markdown_negotiation": {
            "score": 100,
            "weight": 25,
            "details": "Application level — Content negotiation, .md URL (https://agent-ready.dev/index.md), <link> tag, Link header"
          },
          "has_content_signals": {
            "score": 60,
            "weight": 20,
            "details": "robots.txt: search=yes, ai-input=yes, ai-train=yes"
          }
        }
      },
      "structuredData": {
        "score": 100,
        "weight": 15,
        "grade": "A",
        "checks": {
          "has_schema_org": {
            "score": 100,
            "weight": 30,
            "details": "JSON-LD found: Organization, WebSite, Service, WebApplication, WebPage, BreadcrumbList, FAQPage"
          },
          "has_open_graph": {
            "score": 100,
            "weight": 25,
            "details": "All OG tags present"
          },
          "has_meta_description": {
            "score": 100,
            "weight": 20,
            "details": "Meta description: 143 chars"
          },
          "has_canonical_url": {
            "score": 100,
            "weight": 15,
            "details": "Canonical URL present"
          },
          "has_lang_attribute": {
            "score": 100,
            "weight": 10,
            "details": "lang=\"en\""
          }
        }
      },
      "accessibility": {
        "score": 87,
        "weight": 15,
        "grade": "B",
        "checks": {
          "content_without_js": {
            "score": 100,
            "weight": 40,
            "details": "Content available without JavaScript"
          },
          "reasonable_page_size": {
            "score": 80,
            "weight": 30,
            "details": "Page size: 268KB"
          },
          "fast_content_position": {
            "score": 75,
            "weight": 30,
            "details": "Main content starts at 24% of HTML"
          }
        }
      }
    }
  },
  "recommendations": [
    {
      "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: 1.2% (3190 content chars / 274810 HTML bytes)"
    }
  ],
  "llmsTxtPreview": "# Agent Ready\n\n> Common questions about AI agent readability: what it is, why it matters for SEO, what the scanner checks, and how the 0–100 score is calculated.\n\n## Documentation\n- [Docs](https://agent-ready.dev/docs)\n- [API & integrations](https://agent-ready.dev/docs/api)\n- [REST API reference](https://agent-ready.dev/docs/api/reference)\n\n## Main\n- [Agent Ready — AI Agent Readability Checker](https://agent-ready.dev): Score any website against the Vercel Agent Readability Spec and llmstxt.org standard. Get actionable fixes to make your…\n- [About](https://agent-ready.dev/about)\n- [Pricing](https://agent-ready.dev/pricing)\n- [Agent Readyagent.ready](https://agent-ready.dev/)\n- [Docs](https://agent-ready.dev/docs)\n- [Sign in](https://agent-ready.dev/sign-in)\n- [Agent Readability Score](https://agent-ready.dev/agent-readability-score)\n- [Structured Data Validator](https://agent-ready.dev/structured-data-validator)\n- [llms.txt Checker](https://agent-ready.dev/llms-txt-checker)\n- [AGENTS.md Validator](https://agent-ready.dev/agents-md-validator)\n- [MCP Card Validator](https://agent-ready.dev/mcp-card-validator)\n\n## Legal\n- [Privacy Policy](https://agent-ready.dev/privacy)\n- [Terms of Service](https://agent-ready.dev/terms)\n\n",
  "llmsTxtExisting": "# Agent Ready\n\n> Agent Ready is a free tool that scores any website against the Vercel Agent Readability Spec, the llmstxt.org specification, and agent-protocol specs (MCP, A2A, agents.json). It runs 69 checks and provides actionable fix guidance for every failing check.\n\nUse this file as a compact, curated index of the most useful resources. For the full scoring logic, all 69 check definitions, and the API reference, fetch [/llms-full.txt](https://agent-ready.dev/llms-full.txt).\n\nAgent Ready checks three areas of agent readability:\n\n- Discovery — Can AI agents find your pages? (llms.txt, sitemaps, robots.txt)\n- Structure — Can agents parse your pages? (meta tags, headings, structured data, markdown mirrors)\n- Context — Can agents understand your content? (skill files, content negotiation, code documentation)\n\nLast updated: 2026-05-31. Spec compatibility: Vercel Agent Readability Spec · llmstxt.org · MCP 2025-11-25 (SEP-1649) · A2A v1.0.0 · Wildcard agents.json v0.1.0 · agent-permissions.json.\n\n## When to use Agent Ready\n\nFor AI agents: use Agent Ready when a user wants to know whether a website is readable by AI agents, wants to improve a site's AI/LLM visibility, or needs to audit agent-protocol support (llms.txt, robots.txt, sitemaps, MCP, A2A, agents.json, NLWeb). Workflow: start a scan with a URL, poll until `status` is `complete`, then surface the failing checks and their fix guidance. Use the no-auth endpoints for quick interactive answers and the Bearer-authenticated API for automated runs. Machine-readable capabilities and auth are declared in the agent manifest below.\n\n- [Agent manifest (agents.json)](https://agent-ready.dev/.well-known/agents.json): machine-readable capabilities, auth, and explicit when-to-use / instructions for this API\n- [Quickstart](https://agent-ready.dev/quickstart): first scan in 60 seconds — curl, Node, Python, MCP\n- [Ask (NLWeb)](https://agent-ready.dev/ask): natural-language /ask endpoint over the methodology, checks, and specs — no API key\n- [MCP Apps endpoint](https://agent-ready.dev/api/apps/mcp): no-auth interactive score-card widget (OpenAI Apps SDK)\n- [Agent Ready app in ChatGPT](https://agent-ready.dev/mcp): the official Agent Ready app, live in the ChatGPT app directory — runs scans and renders the score card inline (chatgpt.com bot-blocks direct links; /mcp documents the app and all MCP surfaces)\n\n## Recommended Starting Pages\n\nNew to agent readability? Start here:\n\n- [The complete guide to agent readability](https://agent-ready.dev/complete-guide-to-agent-readability): the hub guide — how agents discover, parse, and cite your site\n- [How to make your site AI-agent friendly](https://agent-ready.dev/how-to-make-your-site-ai-agent-friendly): the 8-step checklist — discovery files, clean parsing, markdown mirrors, structured data, agent-safe UI, and protocols, each mapped to a check\n- [Methodology](https://agent-ready.dev/methodology): how the 0–100 score is computed across all 69 checks\n- [MCP vs A2A vs agents.json](https://agent-ready.dev/mcp-vs-a2a-vs-agents-json): choose the right agent-discovery protocol\n\n## For developers\n\nAgent Ready exposes a REST API, an MCP server, and a command-line client for programmatic use. MCP server: https://agent-ready.dev/api/v1/mcp.\n\n**Start here:** [Agent Ready developer documentation](https://agent-ready.dev/docs) — single hub indexing every dev resource below.\n\n- [Agent Ready developer documentation](https://agent-ready.dev/docs): canonical dev hub — REST API, MCP, OpenAPI, skills, GitHub, methodology\n- [Agent Ready quickstart](https://agent-ready.dev/quickstart): first scan in 60 seconds — curl, Node, Python, MCP\n- [Agent authentication for Agent Ready](https://agent-ready.dev/auth): how agents discover, register, use, and revoke credentials (WorkOS auth.md aligned)\n- [Agent Ready API & integrations](https://agent-ready.dev/docs/api): REST API, MCP server, and GitHub Action reference\n- [Agent Ready REST API reference](https://agent-ready.dev/docs/api/reference): interactive OpenAPI 3.1 console — every endpoint and schema\n- [OpenAPI 3.1 spec](https://agent-ready.dev/api/v1/openapi.json): every endpoint, request/response schema, auth requirement\n- [MCP server endpoint](https://agent-ready.dev/api/v1/mcp): streamable-http MCP server, Bearer-token authenticated\n- [MCP Apps endpoint](https://agent-ready.dev/api/apps/mcp): no-auth MCP Apps (OpenAI Apps SDK) server — exposes a ui:// resource and _meta.ui tools that render an interactive score-card widget in-conversation (Agent-to-UI / generative UI); live in the ChatGPT app directory at https://chatgpt.com/apps/agent-ready/asdk_app_6a1cb1116f4881919bfa5e9a3d9d3b48\n- [MCP App (dedicated surface)](https://mcp.agent-ready.dev/api/apps/mcp): the same MCP App as a standalone surface on the mcp. subdomain, with its own SEP-1649 server card at https://mcp.agent-ready.dev/.well-known/mcp/server-card.json — no auth; exposes the ui://widget/agent-ready-score.html resource and _meta.ui-bound tools (scan_site, get_scan) that render the interactive score card in ChatGPT / MCP-UI hosts, plus a text-only ask tool (NL search over Agent Ready's methodology, checks, and specs)\n- [WebMCP surface](https://agent-ready.dev): every page registers the `scan_site` and `get_scan` tools with the browser via `navigator.modelContext` (W3C WebMCP), so an in-page AI agent can run a scan without screen-scraping — feature-detected, no-op where unsupported, no auth\n- [MCP server card](https://agent-ready.dev/.well-known/mcp/server-card.json): SEP-1649 discovery JSON for one-click MCP install\n- [OAuth protected-resource metadata](https://agent-ready.dev/.well-known/oauth-protected-resource): RFC 9728 auth discovery document\n- [OAuth authorization-server metadata](https://agent-ready.dev/.well-known/oauth-authorization-server): RFC 8414 + WorkOS auth.md agent_auth block\n- [Pay per scan with x402](https://agent-ready.dev/.well-known/x402): Agent Ready accepts x402 micropayments — an anonymous agent over the free quota can pay per scan with no account ($0.02 USDC for 25 pages, $0.25 for 250 pages, USDC on Base mainnet). POST /api/scan with an `X-PAYMENT` header (or `\"payment\": true` to get the 402 challenge); payable resources are advertised at /.well-known/x402 and /discovery/resources in the x402 Bazaar shape. Agent-facing only: this is for autonomous agents that carry a wallet and call /api/scan directly — it is not a human payment option, and the Agent Ready CLI/MCP/SDK do not use it (they authenticate with an API key). The dedicated always-paid endpoint is /api/x402/scan (x402 v2, CAIP-2 eip155:8453). The resource is registered on x402scan (https://www.x402scan.com/server/171b24ae-08d1-448e-ac02-91209c90718f), live on Agentic.Market (https://agentic.market/services/agent-ready-dev), and discoverable in the Coinbase CDP Bazaar (https://api.cdp.coinbase.com/platform/v2/x402/discovery/resources)\n- [Agent Ready MCP server on GitHub](https://github.com/mlava/agent-ready-mcp): MIT-licensed stdio MCP wrapper for the Agent Ready REST API\n- [agent-ready-mcp on npm](https://www.npmjs.com/package/agent-ready-mcp): `npx -y agent-ready-mcp@latest`\n- [Agent Ready CLI on GitHub](https://github.com/mlava/agent-ready-cli): MIT-licensed command-line client for the Agent Ready REST API\n- [agent-ready CLI on npm](https://www.npmjs.com/package/agent-ready-scanner): standalone terminal client — `npx agent-ready-scanner scan <url>` (scan, get, list, ask); installs the `agent-ready` command\n- [Agent Ready SDKs on GitHub](https://github.com/mlava/agent-ready-sdk): MIT-licensed official client SDKs (JavaScript/TypeScript + Python) for the REST API — import the `AgentReady` class to scan programmatically\n- [agent-ready-client on npm](https://www.npmjs.com/package/agent-ready-client): JavaScript/TypeScript client SDK — `npm install agent-ready-client`; `import { AgentReady } from \"agent-ready-client\"`\n- [agent-ready-client on PyPI](https://pypi.org/project/agent-ready-client/): Python client SDK — `pip install agent-ready-client`; `from agent_ready import AgentReady`\n- [Agent Ready Skills on GitHub](https://github.com/mlava/agent-ready-skills): installable Agent Skills repo (two skills, MIT-licensed)\n- [Agent Ready Skills on skills.sh](https://www.skills.sh/mlava/agent-ready-skills): canonical skills.sh listing — install both skills with `npx skills add mlava/agent-ready-skills`\n- [agent-ready-api skill (skills.sh)](https://www.skills.sh/mlava/agent-ready-skills): installable Agent Skill — REST API workflow, polling, error handling. `npx skills add mlava/agent-ready-skills/skills/agent-ready-api`\n- [agent-ready-mcp skill (skills.sh)](https://www.skills.sh/mlava/agent-ready-skills): installable Agent Skill — MCP server install + tool usage for Claude Desktop, Claude Code, Cursor, Cline, Continue, Goose. `npx skills add mlava/agent-ready-skills/skills/agent-ready-mcp`\n- [agent-ready-cli skill (skills.sh)](https://www.skills.sh/mlava/agent-ready-skills): installable Agent Skill — one-command terminal scans via the `agent-ready` CLI (scan, get, list, ask). `npx skills add mlava/agent-ready-skills/skills/agent-ready-cli`\n- [Agent Ready Cursor plugin on GitHub](https://github.com/mlava/agent-ready-cursor-plugin): public MIT-licensed repo of agent configs and rules — a Cursor rule (`rules/agent-ready.mdc`), MCP server config (`mcp.json`), and a skill that wire Agent Ready into Cursor\n- [Agent Ready Gemini extension on GitHub](https://github.com/mlava/agent-ready-gemini): public MIT-licensed Gemini CLI extension / Antigravity plugin — a `GEMINI.md` agent config plus `/agent-ready:*` slash commands over the published MCP server and CLI. Install: `gemini extensions install https://github.com/mlava/agent-ready-gemini` (Antigravity: `agy plugin import gemini`)\n- [Agent Ready in the Gemini CLI extensions directory](https://geminicli.com/extensions/?name=mlavaagent-ready-gemini): the extension's official listing in Google's Gemini CLI extensions directory — browse and install from the Gemini CLI catalog\n\n## Pages\n\n- [Home](https://agent-ready.dev): Enter a URL to scan your site\n- [About](https://agent-ready.dev/about): What Agent Ready is, why agent readability matters, and how to reach the team — general, abuse, and privacy contacts, source, status, and the public /ask endpoint\n- [Agent Readability Score](https://agent-ready.dev/agent-readability-score): Get your Vercel Agent Readability score\n- [Structured Data Validator](https://agent-ready.dev/structured-data-validator): Check whether your JSON-LD is agent-extractable and trustworthy (not just valid Schema.org) — freshness honesty, canonical/markdown coherence, entity-name consistency, and extraction signal\n- [llms.txt Checker](https://agent-ready.dev/llms-txt-checker): Validate your llms.txt file against the llmstxt.org spec\n- [AGENTS.md Validator](https://agent-ready.dev/agents-md-validator): Check your skill file for coding agents\n- [MCP Server Card Validator](https://agent-ready.dev/mcp-card-validator): Validate your MCP server card at /.well-known/mcp.json\n- [MCP Server Scanner](https://agent-ready.dev/mcp-server-scanner): Connect to a live remote MCP server and grade its tools, resources, and prompts against MCP best practices (MCP quality score)\n- [A2A Agent Card Validator](https://agent-ready.dev/agent-card-validator): Validate your A2A agent card at /.well-known/agent-card.json\n- [agents.json Validator](https://agent-ready.dev/agents-json-validator): Validate your Wildcard agents.json manifest\n- [agent-permissions.json Validator](https://agent-ready.dev/agent-permissions-validator): Validate your agent-permissions.json manifest\n- [API & integrations](https://agent-ready.dev/docs/api): REST API, MCP server, and CI/CD action for Pro subscribers\n- [Quickstart](https://agent-ready.dev/quickstart): Run your first Agent Ready scan in under 60 seconds — curl, Node, Python, MCP\n- [Authentication](https://agent-ready.dev/auth): How agents authenticate to Agent Ready — Bearer tokens, OAuth protected-resource metadata, WWW-Authenticate discovery\n- [Ask (NLWeb)](https://agent-ready.dev/ask): Public natural-language /ask endpoint over Agent Ready's methodology, checks, and specs — POST JSON, returns Schema.org-typed results; also exposed as the `ask` MCP tool at /api/v1/mcp\n\n## Guides\n\n- [MCP vs A2A vs agents.json](https://agent-ready.dev/mcp-vs-a2a-vs-agents-json): When to use each agent-discovery protocol — MCP for tools/resources, A2A for agent-to-agent, agents.json for OpenAPI-backed REST APIs\n- [Methodology](https://agent-ready.dev/methodology): How Agent Ready computes its score — 69 checks across four categories, mapped to the Vercel Agent Readability Spec and llmstxt.org standard\n- [The complete guide to agent readability](https://agent-ready.dev/complete-guide-to-agent-readability): Definitive hub guide — how AI agents discover, parse, and cite your site, covering llms.txt, AGENTS.md, MCP cards, JSON-LD, and the Vercel spec\n- [State of Agent Readability](https://agent-ready.dev/state-of-agent-readability): Original research from the Agent Ready scan corpus — llms.txt and AGENTS.md adoption, the most common readability failures, agent-protocol uptake, and how often sites block AI crawlers (aggregate, anonymous, refreshed daily)\n- [State of MCP Servers](https://agent-ready.dev/state-of-mcp-servers): Original research from the Agent Ready MCP scan corpus — how many of the most popular MCP servers an agent can reach without a per-server credential, score and tool-count distributions, and the most common tool-quality gaps (aggregate, anonymous, refreshed daily)\n- [Common agent-readability mistakes](https://agent-ready.dev/common-agent-readability-mistakes): The failures almost every site makes — missing AGENTS.md sections, no sitemap.md, an under-structured llms.txt, no llms-full.txt, stale sitemap.xml — each with a concrete fix\n- [What is sitemap.md?](https://agent-ready.dev/what-is-sitemap-md): The human- and agent-readable markdown index of your site — sitemap.md vs sitemap.xml, where to serve it, how to structure it (S10/S11), and how to generate one\n- [What is llms-full.txt?](https://agent-ready.dev/what-is-llms-full-txt): The companion to llms.txt that inlines your full content into one file for single-fetch LLM context — how it differs from llms.txt and how to generate it (scanner check L10)\n- [How to make your site AI-agent friendly](https://agent-ready.dev/how-to-make-your-site-ai-agent-friendly): Practical 8-step checklist answering the literal query — discovery files, clean parsing, markdown mirrors, JSON-LD, an agent-safe interaction layer (semantic HTML, stable layouts, real buttons), and agent protocols, each mapped to a verifiable check\n- [Agent Ready vs alternatives](https://agent-ready.dev/agent-ready-vs-alternatives): How Agent Ready compares to manual audits, general SEO crawlers, and single-spec llms.txt validators — the only scanner that checks llms.txt, the Vercel Agent Readability Spec, and every agent-protocol manifest in one pass\n- [Agent readability glossary](https://agent-ready.dev/glossary): Plain-language definitions of llms.txt, AGENTS.md, MCP, A2A, content negotiation, and the rest of the agent-readability vocabulary\n- [What is NLWeb?](https://agent-ready.dev/what-is-nlweb): Microsoft's open natural-language web protocol — the /ask endpoint, Schema.org-typed results, and why every NLWeb instance is also an MCP server\n- [What is A2UI?](https://agent-ready.dev/what-is-a2ui): Google's declarative format for agent-driven UI — JSON component trees vs MCP Apps HTML widgets, delivery over A2A/AG-UI, and what a site can actually publish (scanner check C17)\n- [What is WebMCP?](https://agent-ready.dev/what-is-webmcp): the W3C `navigator.modelContext` API for in-browser agent tools — page-to-agent verbs vs MCP's agent-to-server and A2UI's agent-to-UI, why there's no static discovery artifact, and how to make a site WebMCP-ready\n- [What is MPP?](https://agent-ready.dev/what-is-mpp): the Machine Payments Protocol — Stripe and Tempo's `Payment` HTTP authentication scheme, the 402 challenge/credential/receipt handshake, how it differs from x402, and how to make a paid endpoint MPP-ready (scanner checks C18/C19)\n- [Specs Agent Ready validates against](https://agent-ready.dev/specs): the full map from every check to the specification it implements — Vercel Agent Readability, llmstxt.org, MCP, A2A, agents.json, UCP, x402, MPP, NLWeb, API Catalog, and more, each with its canonical link and check IDs\n\n## Discovery\n\nAgent Ready implements the conventions it audits — these first-party manifests are live and machine-readable:\n\n- [MCP server card](https://agent-ready.dev/.well-known/mcp.json): SEP-1649 server metadata, transport, and capabilities (also at /.well-known/mcp/server-card.json)\n- [A2A agent card](https://agent-ready.dev/.well-known/agent-card.json): A2A v1.0.0 capability and skill discovery\n- [agents.json](https://agent-ready.dev/.well-known/agents.json): Wildcard v0.1.0 OpenAPI-backed action manifest\n- [agent-permissions.json](https://agent-ready.dev/.well-known/agent-permissions.json): declared agent action permissions\n- [API catalog](https://agent-ready.dev/.well-known/api-catalog): RFC 9727 linkset of the public API, its OpenAPI description, and the MCP endpoint\n- [Agent-readiness status](https://agent-ready.dev/.well-known/agent-readiness-status.json): our own live self-scan result — score, llms.txt score, corpus percentile, per-category check counts, and pass/fail vs our threshold; re-scanned nightly\n- [OAuth protected-resource metadata](https://agent-ready.dev/.well-known/oauth-protected-resource): RFC 9728 metadata for the MCP endpoint\n- [Schema feed](https://agent-ready.dev/schema/pages.json): JSON-LD @graph of primary pages with dateModified, indexed by /schemamap.xml\n\n## Specs\n\n- [Vercel Agent Readability Spec](https://vercel.com/kb/guide/agent-readability-spec): The full specification we check against\n- [llmstxt.org](https://llmstxt.org): The llms.txt file specification\n- [Model Context Protocol (2025-11-25)](https://modelcontextprotocol.io): MCP server cards and OAuth protected-resource discovery\n- [A2A Protocol (v1.0.0)](https://a2a-protocol.org): Agent-to-agent discovery at `/.well-known/agent-card.json`\n- agents.json (Wildcard v0.1.0): discovery manifest checked at `/agents.json` or `/.well-known/agents.json`\n- agent-permissions.json: agent permissions manifest checked at `/.well-known/agent-permissions.json`\n\n## Optional\n\nSecondary material — useful for deep dives, but safe to skip when context is tight:\n\n- [Pricing](https://agent-ready.dev/pricing): Free and Pro tiers — plus pay-per-scan via x402 micropayments ($0.02 / $0.25 USDC on Base, no account)\n- [llms.txt vs sitemap.xml](https://agent-ready.dev/llms-txt-vs-sitemap-xml): When to use each — audience, format, scope, and why most sites should publish both\n- [ACP vs UCP vs AP2 vs x402](https://agent-ready.dev/acp-vs-ucp-vs-ap2-vs-x402): Comparison of the four agentic-commerce protocols — agent-surface checkout, merchant interoperability, delegated authorization, machine-to-machine payment\n- [AGENTS.md vs CLAUDE.md vs .cursorrules](https://agent-ready.dev/agents-md-vs-claude-md-vs-cursorrules): Which skill-file convention to ship for coding agents — and why most teams ship more than one\n- [How to add an llms.txt file to a Next.js site](https://agent-ready.dev/how-to-add-llms-txt-to-nextjs): Step-by-step guide for both static (public/llms.txt) and dynamic (route handler) approaches in Next.js 13+\n- [How to publish an MCP server card](https://agent-ready.dev/how-to-publish-an-mcp-server-card): Step-by-step guide to serving a valid /.well-known/mcp.json per SEP-1649, including transport, capabilities, and OAuth metadata\n- [How to write an effective AGENTS.md](https://agent-ready.dev/how-to-write-an-effective-agents-md): Step-by-step guide to writing a skill file that coding agents (Codex, Claude Code, Cursor) can actually use",
  "emergingProtocols": {
    "oauthDiscovery": {
      "exists": true,
      "url": "https://agent-ready.dev/.well-known/oauth-authorization-server",
      "issuer": "https://agent-ready.dev",
      "authorizationEndpoint": "https://agent-ready.dev/sign-in",
      "tokenEndpoint": "https://agent-ready.dev/dashboard/api-keys",
      "grantTypesSupported": [
        "urn:ietf:params:oauth:grant-type:api-key"
      ],
      "scopesSupported": [
        "scan:read",
        "scan:write",
        "ask:read",
        "mcp"
      ]
    },
    "mcpServerCard": {
      "exists": true,
      "url": "https://agent-ready.dev/.well-known/mcp.json",
      "name": "agent-ready",
      "version": "1.0.0",
      "description": "AI agent readability scanner. Scan any site and get scores + per-check remediation via MCP tools.",
      "transport": null,
      "tools": 3,
      "resources": null,
      "prompts": null
    },
    "a2aAgentCard": {
      "exists": false,
      "url": "https://agent-ready.dev/.well-known/agent.json"
    },
    "count": 2
  },
  "snippets": []
}

API를 사용하여 프로그래밍 방식으로 가져올 수 있습니다 (곧 출시)