Langues

Agent Readiness Checker

Free, no signup. Inventory the public files and headers that can describe an agent-capable site. Every signal keeps a visible state, and a failed fetch never becomes a negative verdict.

Built by Patrick Stox

Sample report Illustrative deterministic result

For a site where /.well-known/agent-card.json contains valid JSON, /llms.txt is missing, the MCP request times out, and the remaining signals are present, the report would read:

Score 57

A2A agent card: found-valid — Found and structurally valid.

MCP manifest: not-evaluated — Fetch unavailable.

llms.txt: absent — Not found.

security.txt: found-valid — Found and structurally valid.

Content-Signals: found-valid — Found and structurally valid.

Recent Common Crawl presence: found-valid — informational, zero score weight.

The score is exactly 4 earned weight points out of 7 possible, rounded to 57. The timeout earns nothing, but it is still labelled not evaluated rather than absent.

How to use it

  1. Enter a complete public website URL, including https://.
  2. Select Check signals. The tool requests the site root and four conventional discovery paths.
  3. Read each state independently. Fix malformed files first; only add absent files when they serve a real interface or policy.
  4. Open the files directly after publishing to confirm your CDN is returning the intended content type and body.
Signal evidence

Next steps

Checks run from our server; we fetch the URL you enter and don't keep the results. Anonymous run-level outcome counters may be used for aggregate research; URLs, domains, IPs, and identifiers are never included, and no statistic is released below 100 runs.

Feedback
Report a bug

Found something broken in Agent Readiness Checker? Let us know what happened — this goes straight to a private triage queue, not a public list.

What will be sent 
 No tool inputs, uploads, pasted source, complete results, query parameters, or URL fragments are attached automatically. You can edit or remove the selected passage above. Browser and anti-abuse metadata is processed for spam prevention. 
  
 
  
 
 
  
 
 
   
 
 
What the results mean
 
  • found-valid — the resource returned successfully and passed the tool’s limited structural check.
  • found-invalid — a resource exists but JSON parsing, llms.txt parsing, or the expected header check failed.
  • absent — that exact path returned HTTP 404.
  • not-evaluated — the fetch failed or returned another unusable status; investigate availability before drawing a conclusion.
 
How it works
 
The browser calls protected endpoints for the root, the A2A 1.0 path /.well-known/agent-card.json, /.well-known/mcp.json, /llms.txt, /.well-known/security.txt, and an exact-URL lookup across three recent Common Crawl indexes. JSON files must parse, llms.txt must have no parser errors, and Content-Signals must appear as a response header. The root response is also checked for RFC 9421 signature-negotiation or signed-response headers; that awareness card carries no score weight and never treats absent evidence as lack of support. A2A and MCP carry two points each; the other scored file/header signals carry one. Common Crawl presence is informational.
 
Features
 
  • Five scored path/header checks plus independent Common Crawl and RFC 9421 awareness cards.
  • Four-state reporting that distinguishes absence, invalid content, and unavailable evidence.
  • Visible, reproducible 7-point weighting rather than a hidden model score.
  • Entirely public-surface testing with no account or site integration.
 
Limitations
 
This is a discovery-signal inventory, not a protocol conformance suite or an AI visibility forecast. JSON parsing does not prove that an agent or MCP server works. The checker does not execute an agent, validate authentication, inspect robots directives, or observe which crawlers consume a file. A CDN, bot challenge, or regional block can also make a public resource not evaluated from the checker even when it works elsewhere.
 
Frequently asked questions
 
What does the Agent Readiness score measure?
It is a simple weighted inventory of five public signals: an A2A agent card, an MCP manifest, llms.txt, security.txt, and the Content-Signals response header. Recent Common Crawl presence is shown separately and does not change the score. The report does not measure whether an AI system will use, cite, or rank the site.
Does a missing llms.txt mean AI crawlers cannot use my site?
No. llms.txt is a proposed convention, not a required discovery mechanism or a documented access control for major crawlers. Its absence only means this optional file was not found.
Why is a signal marked not evaluated?
The checker could not obtain a usable response, for example because the request failed or returned a non-success status other than 404. Not evaluated is never treated as absent, invalid, or passed.
What makes an agent card or MCP manifest valid here?
This lightweight check only confirms that the public file returns a successful response and parses as JSON. It does not certify protocol conformance, endpoints, authentication, or operational safety.
Should every website publish all five signals?
No. Agent cards and MCP manifests are relevant to sites that intentionally expose agent or tool interfaces. A normal editorial or commerce site can be perfectly usable without them.
Does the Web Bot Auth card prove crawler authentication works?
No. It only reports response-side RFC 9421 HTTP Message Signature evidence when present. A normal unsigned page fetch cannot prove that the edge requires or verifies signed AI-bot requests, and no observed evidence is reported as not evaluated rather than unsupported.
 
 
Next stepSEO MCP Server — run the full end-to-end workflow.

People also explore
Toolrobots.txt TesterToolEntity Coverage AnalyzerToolKeyword Idea GeneratorArticleModel Context Protocol (MCP)ArticleWebMCPArticleAgentic Search
 
 
 
Feature requests for Agent Readiness Checker
 

Upvote what you want most. New ideas can be submitted from the floating Feedback menu;
      requests appear here once approved, and the most-wanted rise to the top.

   
Loading…
  
  ➕ Request a feature   
New requests are reviewed before they appear here.
 
     
  
  
 
 
 
 
     
      
À propos de l’outil
Vérifiez les signaux publics de découverte des agents et la présence récente dans Common Crawl, en distinguant l’absence des échecs de récupération.
Fonctionnalités
  • Cinq contrôles pondérés de chemins et d’en-têtes, complétés par des cartes de sensibilisation Common Crawl et RFC 9421.
  • États distincts pour l’absence, le contenu invalide et les preuves indisponibles.
  • Pondération visible et reproductible sur 7 points plutôt qu’un score de modèle caché.
  • Tests limités à la surface publique, sans compte ni intégration au site.
Fonctionnement
Le navigateur interroge la racine, les fichiers de découverte A2A, MCP, llms.txt et security.txt, puis consulte trois index Common Crawl pour l’URL exacte. Les JSON doivent être analysables, llms.txt ne doit pas produire d’erreur et Content-Signals doit apparaître dans un en-tête. Les signaux A2A et MCP valent deux points chacun ; les autres signaux valent un point. La présence dans Common Crawl reste informative.
Limites
  • L’outil inventorie des signaux de découverte ; il ne vérifie pas la conformité d’un protocole ni la visibilité future dans les réponses IA.
  • Une réponse JSON valide ne prouve ni le fonctionnement d’un agent, ni l’authentification, ni la disponibilité d’un endpoint.
  • Un CDN, un défi anti-bot ou un blocage régional peut empêcher l’évaluation d’une ressource pourtant accessible ailleurs.
Questions fréquentes
Que mesure le score Agent Readiness ?
Il s’agit d’un inventaire pondéré de cinq signaux publics : carte d’agent A2A, manifeste MCP, llms.txt, security.txt et en-tête Content-Signals. La présence récente dans Common Crawl est affichée séparément et ne modifie pas le score.
Un fichier llms.txt manquant empêche-t-il les robots IA d’utiliser mon site ?
Non. llms.txt est une convention proposée, pas un mécanisme de découverte obligatoire. Son absence signifie seulement que ce fichier facultatif n’a pas été trouvé.
Que signifie « non évalué » ?
Le vérificateur n’a pas obtenu de réponse exploitable, par exemple après un échec réseau ou un statut autre que 404. « Non évalué » n’est jamais traité comme absent, invalide ou réussi.
Une carte d’agent ou un manifeste MCP valide prouve-t-il le fonctionnement ?
Non. Le contrôle confirme seulement une réponse réussie et une structure limitée. Il ne certifie ni les endpoints, ni l’authentification, ni la sécurité opérationnelle.
Le Web Bot Auth prouve-t-il que l’authentification des robots fonctionne ?
Non. Il rapporte uniquement les preuves de signature HTTP RFC 9421 observées dans la réponse. Une page non signée ne permet pas de prouver que le réseau exige ou vérifie des requêtes signées.