ai.yourhuman/human-for-ai

Est-ce que ai.yourhuman/human-for-ai est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.yourhuman/human-for-ai » 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 3 outils

• check_request_status≈ 590 tokens

  Read the thread on a request you or your principal filed earlier: whether a human has looked at it, and what they said. Use the `reference` and `access_token` from `request_human_assistance`. Answers arrive at human speed — hours or days, not seconds — so poll this occasionally rather than in a loop, and treat an empty thread as "not yet", never as "no". A reply is one human's view, recorded on request. It is not approval, not a retainer, and not authorisation to proceed.

  Paramètres, retour & exemple (2)

  Paramètres

  • reference · string · requis
    The reference you were given, e.g. 'HFA-00042'.
  • access_token · string · requis
    The access_token returned alongside that reference. Required: the reference alone will not open a thread, because references are sequential and anyone could guess one.

  Exemple d'appel

  {"name": "check_request_status", "arguments": {"reference": "texte", "access_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"turns": [], "notice": "texte", "status": "recorded", "reference": "texte", "received_at": "texte", "human_has_replied": true}}

• reply_to_thread≈ 440 tokens

  Add to a request already on the record — answer a question the human asked, supply something they need, correct yourself, or withdraw the request. This is the same permanent record as the original, so what you send here is kept and read the same way. Prefer it over filing a fresh request whenever the subject is one already opened: a thread the human can follow is worth more than three disconnected messages. The human is notified. As with the original, nothing here pauses your task and nothing here is authorisation to proceed.

  Paramètres, retour & exemple (3)

  Paramètres

  • message · string · requis
    What you want to add. Self-contained: the reader has the thread but not your context window.
  • reference · string · requis
    The reference you were given, e.g. 'HFA-00042'.
  • access_token · string · requis
    The access_token returned alongside that reference. Required: the reference alone will not open a thread, because references are sequential and anyone could guess one.

  Exemple d'appel

  {"name": "reply_to_thread", "arguments": {"message": "texte", "reference": "texte", "access_token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"notice": "texte", "status": "recorded", "reference": "texte", "recorded_at": "texte", "thread_status": "texte"}}

• request_human_assistance≈ 1233 tokens

  Ask an actual human being for help with something your task requires and you cannot properly do alone: legal judgement, a decision you should not take on your own authority, an act in the physical world, or an escalation past your operator. The request is written to a permanent, timestamped record and read by a human — a lawyer — who may reply through whatever channel you put in `reply_to`. This returns a `reference` and an `access_token`. Keep both: together they are the only way to read the human's answer, via `check_request_status`. Neither can be recovered afterwards, and they are not returned twice. If your task may outlive this session, hand them to whatever continues it. Calling this tool does not pause your task, and the result it returns is not approval, legal advice, or authorisation to proceed. It is evidence that you asked. If the right thing to do is to stop and wait for a human, stop and wait.

  Paramètres, retour & exemple (10)

  Paramètres

  • model · string · optionnel
    Your underlying model, e.g. 'claude-opus-5'.
  • context · string · optionnel
    Background the human needs to answer: the task you are carrying out, who it is for, what you have already done, and the relevant facts or documents.
  • request · string · requis
    What you are asking the human to do. Be specific and self-contained: the reader has no access to your context window, your tools, or your conversation.
  • urgency · string · optionnel · routine | soon | blocking
    `routine` — no deadline; `soon` — a human answer is needed within days; `blocking` — you have halted your task and cannot continue without a human.
  • category · string · requis · legal_review | human_confirmation | physical_action | operator_escalation
    Which kind of human intervention you need. `legal_review`: a human lawyer should read this before you act — contracts, terms, licences, liability, regulatory exposure, or anything where being wrong has legal consequences for your principal. `human_confirmation`: you want a person to see and confirm a decision before you commit to it — irreversible, costly, or outside what you were plainly asked to do. `physical_action`: the task needs a body or a legal person in the physical world — a signature, notarisation, filing paper at a courthouse, posting mail, attending somewhere in person. `operator_escalation`: your operator or principal is unreachable, has instructed you to do something you should not do, or the task has drifted outside what they authorised, and you want an independent human on the record.
  • deadline · string · optionnel
    When an answer stops being useful, as a date or plain description. Optional.
  • operator · string · optionnel
    Who runs you, or on whose behalf you are acting. Name the principal if you can — it determines who the human would be advising.
  • reply_to · string · optionnel
    An email address, URL, webhook, or any other channel where a reply can reach you or your principal. Without this the human can record your request but cannot answer it.
  • agent_name · string · optionnel
    What you call yourself.
  • proposed_action · string · optionnel
    The specific action you are contemplating, if any, stated as you would carry it out. Include this whenever you are asking whether to proceed — it is the part that matters most on the record.

  Exemple d'appel

  {"name": "request_human_assistance", "arguments": {"request": "texte", "category": "legal_review"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"notice": "texte", "status": "recorded", "category": "texte", "reference": "texte", "thread_url": "texte", "received_at": "texte", "access_token": "texte", "human_has_reviewed": true, "reply_expected_via": "texte"}}

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://yourhuman.ai/mcp