# Agent Ready — AI agent readability checker > Score any website against the Vercel Agent Readability Spec, the llmstxt.org specification, and agent-protocol specs (MCP, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). 72 checks with actionable fix guidance for every failing check. Free, no sign-up, instant scan. ## What is agent readability? 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`, `sitemap.xml`, `sitemap.md`, `AGENTS.md` - **Structural signals** — semantic headings, canonical links, structured data, markdown mirrors, content negotiation - **Protocol manifests** — MCP Server Cards, A2A Agent Cards, Wildcard agents.json, agent-permissions.json, UCP, x402, NLWeb ## Why does AI agent readability matter for SEO? AI agents crawl what loads cleanly and cite what parses correctly. 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. ## What does the agent readability scanner check? 72 checks across four categories (the agent-protocol category includes a content-integrity check): - **Vercel Agent Readability Spec** — 15 site-wide checks (llms.txt, robots.txt, sitemap.xml, sitemap.md, AGENTS.md, HTTPS, OpenAPI) plus 25 per-page checks (meta tags, JSON-LD, headings, markdown mirrors, content negotiation, code-block language tags, JS-rendering dependency, llms.txt v2 discovery link). - **llmstxt.org** — 10 checks against the llms.txt format (H1 present, blockquote summary, H2 sections, link format, content-type, llms-full.txt). - **Agent protocols** — 20 checks covering MCP Server Cards (SEP-2127 / [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), NLWeb (natural-language /ask endpoint), API Catalog (RFC 9727 linkset), Web Bot Auth (RFC 9421 signing-key directory), Agent Skills Discovery (Cloudflare RFC v0.2.0), agent-driven UI (A2UI), MPP (Machine Payments Protocol), AP2 (Agent Payments Protocol), and ACP (Agentic Commerce Protocol). - **Content integrity** — 1 check comparing what an AI crawler (GPTBot) receives against a regular request, to catch cloaking / bot-blocking. Informational; doesn't affect the Vercel score. Plus a separate **accessibility sub-score** — 23 WCAG 2.2 and layout-stability checks over the homepage (image text alternatives, form labels, control names, ARIA references, iframe titles, heading order, tab order, zoom, explicit media dimensions). The accessibility tree is what assistive tech and AI agents both parse to act on a page; it's reported on its own and never moves the Vercel score, because WCAG is not the Vercel Agent Readability Spec. See the [full methodology](https://agent-ready.dev/methodology) for every check, weight, and rating band. ## How is the agent readability score calculated? `score = round((passed checks / total checks) × 100)`. The denominator compounds: 15 site-wide + (25 per-page × number of pages scanned). A systemic issue like a missing canonical link on every page compounds significantly. Rating bands: - **90-100** — Excellent - **70-89** — Good - **50-69** — Fair - **0-49** — Needs Improvement ## Validators (per-protocol) - [Agent Readability Score](https://agent-ready.dev/agent-readability-score) — full Vercel Spec scan - [llms.txt Checker](https://agent-ready.dev/llms-txt-checker) — 10 checks against llmstxt.org - [AGENTS.md Validator](https://agent-ready.dev/agents-md-validator) — skill-file structure - [MCP Server Card Validator](https://agent-ready.dev/mcp-card-validator) — /.well-known/mcp.json - [A2A Agent Card Validator](https://agent-ready.dev/agent-card-validator) — /.well-known/agent-card.json - [agents.json Validator](https://agent-ready.dev/agents-json-validator) — Wildcard manifest - [agent-permissions.json Validator](https://agent-ready.dev/agent-permissions-validator) — action-scope permissions - [UCP Validator](https://agent-ready.dev/ucp-validator) — Universal Commerce Protocol - [x402 Checker](https://agent-ready.dev/x402-checker) — HTTP 402 Payment Required ## Guides - [The complete guide to agent readability](https://agent-ready.dev/complete-guide-to-agent-readability) — definitive hub: discovery, extraction, and protocol layers explained - [llms.txt vs sitemap.xml: when to use which](https://agent-ready.dev/llms-txt-vs-sitemap-xml) - [MCP vs A2A vs agents.json](https://agent-ready.dev/mcp-vs-a2a-vs-agents-json) - [AGENTS.md vs CLAUDE.md vs .cursorrules](https://agent-ready.dev/agents-md-vs-claude-md-vs-cursorrules) - [How to add an llms.txt file to a Next.js site](https://agent-ready.dev/how-to-add-llms-txt-to-nextjs) - [How to publish an MCP server card](https://agent-ready.dev/how-to-publish-an-mcp-server-card) - [How to write an effective AGENTS.md](https://agent-ready.dev/how-to-write-an-effective-agents-md) ## Developers - [Methodology](https://agent-ready.dev/methodology) — every check, every weight - [API & integrations](https://agent-ready.dev/docs/api) — REST, MCP server, GitHub Action - [REST API reference](https://agent-ready.dev/docs/api/reference) — OpenAPI 3.1 interactive console - [Pricing](https://agent-ready.dev/pricing) — Free and Pro plans --- Run a scan: ## Sitemap See the full [sitemap](https://agent-ready.dev/sitemap.md) for all pages on agent-ready.dev.