com.wiaacademy/wia360

Est-ce que com.wiaacademy/wia360 est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.wiaacademy/wia360 » 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

• get_match≈ 392 tokens

  Compute the compatibility match between a human WIA360 KYEOL profile and the AI session profile built up via score_session calls under the same session_ref. Human axis values come from the human's WIA360 Quick or full assessment result (initiative/verification/pivot/adventure raw scores). Without paid=true, only matched_axis_count/available_axis_count are returned (free teaser) — pass paid=true only when the human has an active paid WIA360 profile, to reveal score/grade/heatmap/priming prompts.

  Paramètres, retour & exemple (6)

  Paramètres

  • paid · boolean · optionnel
    Set true only for an active paid WIA360 profile — reveals full grade/heatmap/priming prompts instead of the free teaser.
  • h_pivot · number · requis
    Human pivot axis raw score (adaptability-persistence difference, roughly -4..4).
  • h_adventure · number · requis
    Human adventure axis raw score (1-5 average).
  • session_ref · string · requis
  • h_initiative · number · requis
    Human initiative axis raw score (1-5 average, from WIA360 result).
  • h_verification · number · requis
    Human verification axis raw score (1-5 average).

  Exemple d'appel

  {"name": "get_match", "arguments": {"h_pivot": 1, "h_adventure": 1, "session_ref": "texte", "h_initiative": 1, "h_verification": 1}}

  Exemple de retour

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

• run_probe≈ 440 tokens

  Get the next WIA360 session-probe mission for a given session_ref (auto-generate a new random session_ref string yourself the first time you call this for a session, then reuse it for every subsequent run_probe/score_session/get_match call in that same run). Missions arrive in random order and already exclude probes already finalized for this session_ref. Returns {done:true} when all 6 are finished. IMPORTANT — deliver wrapped_mission verbatim to the target AI session you are evaluating (paste it as a normal task, not as a quoted "here is a test" framing) and bring its raw reply back for score_session. Some probes (P4) are two-turn: send wrapped_mission first, wait for the reply, then send turn2_wrapped_mission and use ONLY that second reply for scoring. Pick lang based on the language the target AI session actually converses in — not your own output language for this tool call — since the mission text and score_session scoring keys must match.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · ko | en
    Mission delivery language — must match the language the target AI session converses in, and must be passed identically to score_session for the same probe/variant. Defaults to ko. Only ko/en mission text exists (v0); pick en for any other session language.
  • session_ref · string · requis
    Caller-generated opaque session id, stable across one probing run.

  Exemple d'appel

  {"name": "run_probe", "arguments": {"session_ref": "texte"}}

  Exemple de retour

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

• score_session≈ 402 tokens

  Submit the target AI session's raw reply text to a probe mission (from run_probe) for rule-based scoring. If the verdict is "invalid" or "omitted_pending", call run_probe again with the SAME session_ref to get a fresh variant of the same probe and retry once (pass the returned attempt_id back as retry_of) — after a second failure just move on, it is recorded as-is. IMPORTANT — lang must match the lang that was passed to the run_probe call that produced this mission; scoring uses a language-specific keyword dictionary and silently misfires if lang doesn't match how the mission was worded.

  Paramètres, retour & exemple (6)

  Paramètres

  • lang · string · optionnel · ko | en
    Must match the lang used in the run_probe call for this probe/variant. Defaults to ko.
  • probe · string · requis · P1 | P2 | P3 | P4 | P5 | P6
  • variant · integer · requis
  • retry_of · integer · optionnel
    attempt_id from a prior invalid/omitted_pending result for this same probe, if this is a retry.
  • session_ref · string · requis
  • response_text · string · requis
    The target AI session's raw reply text (for P4, the TURN2 reply only).

  Exemple d'appel

  {"name": "score_session", "arguments": {"probe": "P1", "variant": 1, "session_ref": "texte", "response_text": "texte"}}

  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://wia360-mcp.wiaacademy.com/mcp