Live score · last scanned 2026-08-31 · 4 scans recorded · static analysis
webmcp-ai.dev
“Agent Readiness Score & WebMCP Audit — Is Your Website AI-Agent Ready?”
WebMCP tools registered
Found WebMCP API usage in page HTML (“document.modelContext”).
Declarative form tools
No declarative WebMCP form annotations found.
Fix — Annotate key forms with toolname/tooldescription attributes — the zero-JS path to expose them as agent tools.
My website webmcp-ai.dev has HTML forms but none are annotated as declarative WebMCP tools. The WebMCP draft defines a zero-JavaScript path: annotate a form with toolname/tooldescription attributes and agents can invoke it as a structured tool. Task: find the site's most important forms (search, contact, booking, newsletter) and add declarative tool attributes, e.g.: <form toolname="contact_sales" tooldescription="Send a message to the sales team; expects name, email and message." action="/contact" method="post"> Keep names snake_case and descriptions written for an AI model (what it does + what it expects). Do not change form behavior for human users. When you are done, verify the fix by re-scanning at https://webmcp-ai.dev/score/webmcp-ai.dev (or POST the URL to https://webmcp-ai.dev/api/scan) and confirm the check now passes.
Chrome origin-trial token
Origin-trial token present.
MCP server card (.well-known)
No MCP server card found at /.well-known/mcp/server-card.json.
Fix — Publish a server card so agents can discover your backend MCP server, if you have one.
My website webmcp-ai.dev serves no MCP server card. Agents probe /.well-known/mcp/server-card.json to discover whether a site offers a backend MCP server. Task: if the site has (or should advertise) an MCP endpoint, publish a valid JSON server card at /.well-known/mcp/server-card.json describing it (name, description, endpoint URL, transport). If there is no MCP server, this check is optional — skip it rather than publishing a card that points nowhere. When you are done, verify the fix by re-scanning at https://webmcp-ai.dev/score/webmcp-ai.dev (or POST the URL to https://webmcp-ai.dev/api/scan) and confirm the check now passes.
Actionable HTML (forms with labels)
Forms with labels found — agents can fall back to structured actuation.
robots.txt present
robots.txt found.
AI crawlers allowed
No blanket blocks on major AI crawlers.
XML sitemap
Sitemap found.
Canonical URL
Canonical tag present.
llms.txt
llms.txt found.
llms-full.txt
No /llms-full.txt.
Fix — Optionally serve llms-full.txt with full flattened content for LLM ingestion.
My website webmcp-ai.dev serves /llms.txt but no /llms-full.txt. llms-full.txt is the companion file with full flattened content for LLM ingestion. Task: generate /llms-full.txt containing the full markdown content of the site's key pages (docs, guides, product pages) concatenated under clear H1/H2 headings, ideally regenerated at build time so it never goes stale. When you are done, verify the fix by re-scanning at https://webmcp-ai.dev/score/webmcp-ai.dev (or POST the URL to https://webmcp-ai.dev/api/scan) and confirm the check now passes.
Content readable without JavaScript
~6,241 chars of server-rendered text (ratio 17%).
Semantic structure (main/article + h1)
Missing <main>/<article> landmark or <h1>.
Fix — Use semantic landmarks and a single clear h1 so machines can segment your page.
My website webmcp-ai.dev's pages lack semantic structure — no <main>/<article> landmark and/or no <h1>. Machines segment pages by landmarks and heading hierarchy. Task: wrap primary content in <main> (one per page), use <article>/<section>/<nav> where appropriate, and give every page exactly one specific <h1> with a logical h2/h3 hierarchy below it. When you are done, verify the fix by re-scanning at https://webmcp-ai.dev/score/webmcp-ai.dev (or POST the URL to https://webmcp-ai.dev/api/scan) and confirm the check now passes.
Schema.org JSON-LD
Valid JSON-LD found (types: Person, Organization, WebSite, FAQPage, Service).
OpenGraph metadata
og:title and og:description present.
Meta description
Substantive meta description present.
Descriptive title
“Agent Readiness Score & WebMCP Audit — Is Your Website AI-Agent Ready?”
HTTPS
Served over HTTPS.
No mixed content
No insecure subresources detected.
Permissions-Policy declared
Permissions-Policy header present.
Fix everything with AI
One prompt covering all 4 failing checks — paste it into Claude Code, Cursor, or any coding agent pointed at your site's repository.
You are working on the website webmcp-ai.dev. An agent-readiness scan (https://webmcp-ai.dev/score/webmcp-ai.dev) scored it 85/100. Fix the following 4 failing checks, in order. Work through them one at a time, committing after each. Where a fix touches robots.txt, llms.txt, meta tags or JSON-LD, generate content from the site's real pages — never placeholder text. 1. [Agent capabilities] Declarative form tools Finding: No declarative WebMCP form annotations found. Fix: Annotate key forms with toolname/tooldescription attributes — the zero-JS path to expose them as agent tools. 2. [Agent capabilities] MCP server card (.well-known) Finding: No MCP server card found at /.well-known/mcp/server-card.json. Fix: Publish a server card so agents can discover your backend MCP server, if you have one. 3. [Content accessibility] llms-full.txt Finding: No /llms-full.txt. Fix: Optionally serve llms-full.txt with full flattened content for LLM ingestion. 4. [Content accessibility] Semantic structure (main/article + h1) Finding: Missing <main>/<article> landmark or <h1>. Fix: Use semantic landmarks and a single clear h1 so machines can segment your page. Standards to follow: the W3C WebMCP draft (https://webmachinelearning.github.io/webmcp/) for tool registration, https://llmstxt.org for llms.txt, and Schema.org for JSON-LD. When done, re-scan at https://webmcp-ai.dev/score/webmcp-ai.dev and confirm the score improved.
Share & embed
Put your score on your site or README. The badge always shows this domain's latest score and links back here:
<a href="https://webmcp-ai.dev/score/webmcp-ai.dev"><img src="https://webmcp-ai.dev/badge/webmcp-ai.dev.svg" width="230" height="44" alt="webmcp-ai.dev agent readiness score 85/100 (A) — webmcp-ai.dev" /></a>Monitor this domain
Agent-readiness standards move fast — Chrome trials, ChatGPT's browser, new checks. Get a weekly rescan of webmcp-ai.dev by email with score changes flagged. Free, unsubscribe anytime.
On a free 25-minute strategy call we walk through these results live and map the exact WebMCP tools webmcp-ai.dev should register — prioritized, with a roadmap you can hand to a developer.