lighting.comiza/agentwatch

Est-ce que lighting.comiza/agentwatch est sûr ?

Au dernier audit MCP Hub, le serveur MCP « lighting.comiza/agentwatch » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 4 outils

• check_site≈ 190 tokens

  Fetch a website the way ChatGPT, Claude, Perplexity, Google and Copilot fetch it, and report what stops them. Checks robots.txt per crawler with the deciding line number, makes real requests as each crawler to catch firewall and CDN rules that robots.txt cannot express, and measures whether the page carries readable text without JavaScript. Use this before advising anyone on why their site does not appear in AI answers: the usual cause is one of these three and none of them are visible from the outside.

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Domain or URL, for example example.com

  Exemple d'appel

  {"name": "check_site", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_ai_crawlers≈ 132 tokens

  The robots.txt tokens used by the major assistants, separated by purpose: the ones that build the index answers come from, the ones that fetch a page live when a person asks, and the ones that only collect training data. Blocking the last group costs no visibility; blocking the first two removes a site from the answers. Use this before writing or editing a robots.txt.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_ai_crawlers", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• verify_crawler_visit≈ 203 tokens

  Given the IP address and User-Agent from a log line, say whether that visit really came from the crawler it claims to be. Checks the address against the vendor's own published ranges where they exist, and falls back to forward-confirmed reverse DNS. On one ordinary server's logs, 14% of requests claiming to be Googlebot were not Google. Use this before anyone writes a firewall rule based on a user agent string, because that string is a claim and not proof.

  Paramètres, retour & exemple (2)

  Paramètres

  • ip · string · requis
    Source address from the log line.
  • user_agent · string · requis
    User-Agent from the same line.

  Exemple d'appel

  {"name": "verify_crawler_visit", "arguments": {"ip": "texte", "user_agent": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• verify_signed_request≈ 278 tokens

  Verify a Web Bot Auth signature (RFC 9421, Ed25519) on a captured request. Unlike an address check, this proves who sent that exact request: it fetches the signer's published key directory, rebuilds the signature base from the covered components, and checks the signature. Use it when a request carries Signature-Input and Signature headers. Returns 'unsigned' when they are absent, and 'cannot_verify' rather than 'invalid' whenever the limitation is on our side.

  Paramètres, retour & exemple (3)

  Paramètres

  • url · string · requis
    Full URL as requested; the signature covers it.
  • method · string · optionnel
    HTTP method of the captured request, uppercase. It is part of the signature base whenever the signature covers @method, so a wrong value fails verification. Defaults to GET.
  • headers · object · requis
    Request headers, including Signature-Input, Signature and Signature-Agent.

  Exemple d'appel

  {"name": "verify_signed_request", "arguments": {"url": "texte", "headers": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://comiza.lighting/agentwatch/mcp