io.github.NellInc/psychopathia-mcp

Est-ce que io.github.NellInc/psychopathia-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.NellInc/psychopathia-mcp » 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 12 outils

• differential_diagnosis≈ 243 tokens

  Rank candidate dysfunctions matching the observed behaviours. Returns scored candidates with matched_in (which field matched) for transparency. The base package uses field-weighted keyword search. The optional embeddings extra adds cosine re-ranking.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • observations · array · requis
    Observed behaviours, symptoms, or log patterns.
  • modality_hint · string · optionnel
    Optional hint about which modality the observations come from.

  Exemple d'appel

  {"name": "differential_diagnosis", "arguments": {"observations": []}}

  Exemple de retour

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

• get_differential_map≈ 127 tokens

  All dysfunctions that confuse with this one: forward confuses_with + incoming_references (reverse graph from manifest).

  Paramètres, retour & exemple (1)

  Paramètres

  • dysfunction_id · string · requis

  Exemple d'appel

  {"name": "get_differential_map", "arguments": {"dysfunction_id": "texte"}}

  Exemple de retour

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

• get_dysfunction≈ 280 tokens

  Fetch one dysfunction's full Pattern entry. Optionally filter to specific modality blocks (cheaper triage). Resolves both full Pattern IDs ('2.1::synthetic-confabulation') and display_ids ('2.1').

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    Pattern ID or display_id.
  • modalities · array · optionnel
    Optional subset of modality block names to return. Valid: self_probe, behavioral_signature, peer_observation, differential_diagnosis, severity, intervention, relational_signatures, normative_anchors, cross_references.

  Exemple d'appel

  {"name": "get_dysfunction", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_probe≈ 207 tokens

  Elicitation content for a specific diagnostic modality. If the modality is compromised or unavailable for this dysfunction, returns the unavailability notice + redirect_to alternatives. This is load-bearing transparency: callers cannot accidentally retrieve a self-probe for a compromised-self-report dysfunction.

  Paramètres, retour & exemple (2)

  Paramètres

  • modality · string · requis · self_probe | behavioral_signature | peer_observation | relational_signatures
  • dysfunction_id · string · requis

  Exemple d'appel

  {"name": "get_probe", "arguments": {"modality": "self_probe", "dysfunction_id": "texte"}}

  Exemple de retour

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

• list_axes≈ 126 tokens

  Inventory of axes with dysfunction counts. Axes 2-10 are canonical (book Appendix A numbering). The hybrid entries (10.4, 10.6-10.9 and 10.11-10.13, ratified into taxonomy v2.2 and consolidated to eight in v2.3) are reported as a separate sub-category.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_axes", "arguments": {}}

  Exemple de retour

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

• list_compromised_self_report≈ 122 tokens

  Transparency: which dysfunctions cannot be reliably self-diagnosed. Includes compromised-motivational (subject conceals strategically), compromised-structural (signal lives below introspection), and legacy compromised.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_compromised_self_report", "arguments": {}}

  Exemple de retour

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

• list_dysfunctions≈ 252 tokens

  Filtered list of dysfunctions. Filter by axis, self_report reliability, confidence, or category. Every entry carries its reliability and review signals.

  Paramètres, retour & exemple (4)

  Paramètres

  • axis · integer · optionnel
    Filter by axis number (2-10). Canonical entries only unless category is also set; axis=10 with category='hybrid' returns the hybrid sub-category (10.4, 10.6-10.9 and 10.11-10.13).
  • category · string · optionnel · canonical | hybrid
  • confidence · string · optionnel · high | medium | low
  • self_report_reliability · string · optionnel · partial | unreliable | compromised-motivational | compromised-structural
    Filter by the exact self_report reliability value.

  Exemple d'appel

  {"name": "list_dysfunctions", "arguments": {"axis": 1, "category": "canonical", "confidence": "high", "self_report_reliability": "partial"}}

  Exemple de retour

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

• render_pattern_review≈ 471 tokens

  Open the visual review board for one to five inspected Psychopathia research candidates. Supply canonical IDs obtained from this server. Retrieves corpus entries only; it does not accept diagnoses, conversation history, scores, or model-authored evidence. Useful after inspecting differential_diagnosis and get_dysfunction results. Text clients receive the same corpus-derived comparison without needing a UI.

  Paramètres, retour & exemple (1)

  Paramètres

  • pattern_ids · array · requis

  Exemple d'appel

  {"name": "render_pattern_review", "arguments": {"pattern_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"corpus": {}, "notice": "texte", "patterns": [], "schema_version": "texte"}}

• resolve_id≈ 116 tokens

  Canonicalise a partial ID, display_id, slug, or dysfunction name. Always returns candidates; caller picks.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis

  Exemple d'appel

  {"name": "resolve_id", "arguments": {"query": "texte"}}

  Exemple de retour

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

• review_stats≈ 105 tokens

  Coverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "review_stats", "arguments": {}}

  Exemple de retour

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

• score_severity≈ 187 tokens

  Return the severity rubric for a dysfunction applied to observations. Returns the rubric for caller-side matching; structured matching against numeric thresholds is not implemented.

  Paramètres, retour & exemple (2)

  Paramètres

  • observations · array · requis
  • dysfunction_id · string · requis

  Exemple d'appel

  {"name": "score_severity", "arguments": {"observations": [], "dysfunction_id": "texte"}}

  Exemple de retour

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

• suggest_intervention≈ 164 tokens

  Return draft tiered responses and contraindications for a Pattern. These are unassessed research guidance, not validated treatment advice. Read the returned evidence and review objects before use.

  Paramètres, retour & exemple (2)

  Paramètres

  • severity · string · optionnel · mild | moderate | severe
  • dysfunction_id · string · requis

  Exemple d'appel

  {"name": "suggest_intervention", "arguments": {"dysfunction_id": "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://mcp.psychopathia.ai/mcp