com.pearl.mcp/pearl-api-mcp-server

Est-ce que com.pearl.mcp/pearl-api-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.pearl.mcp/pearl-api-mcp-server » 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 7 outils

• askExpert≈ 378 tokens

  Use this when the user explicitly asks to speak with a real human expert, needs personalized advice in a complex or sensitive domain, or says something like 'Can I talk to a real expert?'. Supports phone callback — pass phoneNumber and contactPreference='phone' if the user wants a call.

  Paramètres, retour & exemple (6)

  Paramètres

  • question · string · requis
    The user's question
  • sessionId · string · optionnel
    Optional session ID for continuing a conversation
  • chatHistory · array · optionnel
    Optional conversation history. This ensures experts see the complete context
  • phoneNumber · string · optionnel
    Customer's phone number for expert callback in E.164 format (e.g., +15551234567). Only pass when the user explicitly provides it.
  • contactPreference · string · optionnel · chat | phone
    Customer's preferred contact method. Set to 'phone' when the user wants a phone callback.
  • enableMockResponse · boolean · optionnel
    When true, the API returns a hardcoded mock expert success response instead of routing to a real expert. Useful for testing downstream behavior.

  Exemple d'appel

  {"name": "askExpert", "arguments": {"question": "texte"}}

  Exemple de retour

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

• askPearlAi≈ 236 tokens

  Use this when the user wants a rapid AI-generated answer, draft, or alternative perspective on a low-risk or exploratory topic that does not require human validation. Do not use for medical, legal, financial, or safety-critical questions — use askExpert or askPearlExpert instead.

  Paramètres, retour & exemple (3)

  Paramètres

  • question · string · requis
    The user's question
  • sessionId · string · optionnel
    Optional session ID for continuing a conversation
  • chatHistory · array · optionnel
    Optional conversation history. This ensures experts see the complete context

  Exemple d'appel

  {"name": "askPearlAi", "arguments": {"question": "texte"}}

  Exemple de retour

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

• askPearlExpert≈ 404 tokens

  Use this when the problem is complex, ambiguous, high-stakes, or multidisciplinary and would benefit from AI intake followed by escalation to a human expert. Do not use for simple fact queries (use askPearlAi) or when the user explicitly requests a human directly (use askExpert). Supports phone callback — pass phoneNumber and contactPreference='phone' if the user wants a call.

  Paramètres, retour & exemple (6)

  Paramètres

  • question · string · requis
    The user's question
  • sessionId · string · optionnel
    Optional session ID for continuing a conversation
  • chatHistory · array · optionnel
    Optional conversation history. This ensures experts see the complete context
  • phoneNumber · string · optionnel
    Customer's phone number for expert callback in E.164 format (e.g., +15551234567). Only pass when the user explicitly provides it.
  • contactPreference · string · optionnel · chat | phone
    Customer's preferred contact method. Set to 'phone' when the user wants a phone callback.
  • enableMockResponse · boolean · optionnel
    When true, the API returns a hardcoded mock expert success response instead of routing to a real expert. Useful for testing downstream behavior.

  Exemple d'appel

  {"name": "askPearlExpert", "arguments": {"question": "texte"}}

  Exemple de retour

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

• getConversationHistory≈ 113 tokens

  Retrieve the full message history for a session. Includes all messages (after any formatting done during processing). Use to resume discussions.

  Paramètres, retour & exemple (1)

  Paramètres

  • sessionId · string · requis
    The session ID of the conversation

  Exemple d'appel

  {"name": "getConversationHistory", "arguments": {"sessionId": "texte"}}

  Exemple de retour

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

• get_verification_state≈ 546 tokens

  Use this when polling the current status of a verification request previously submitted via send_answer_for_verification. Returns the verification state (not started, in progress, or completed) and the expert's verdict once the review is complete.

  Paramètres, retour & exemple (1)

  Paramètres

  • sessionId · string · requis
    The session identifier of the chat whose verification state should be retrieved. Must match the sessionId previously returned by send_answer_for_verification.

  Exemple d'appel

  {"name": "get_verification_state", "arguments": {"sessionId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "NotStarted", "success": true, "expertProfile": {}, "isAnswerCorrect": true}}

• send_answer_for_verification≈ 832 tokens

  Use this tool only when the user explicitly requests to start verification, fact-checking, or expert validation of an AI-generated answer. This tool must be used exclusively to initiate the verification process. Do not call it to check status, retrieve results, or for any follow-up actions. A human Pearl expert will review the answer and determine its correctness. Only one verification is allowed per chat session — this tool must not be invoked more than once. Invoking this tool renders an interactive UI component that displays live verification status and the final expert verdict.

  Paramètres, retour & exemple (2)

  Paramètres

  • conversation · array · requis
    Full conversation between the user and the AI assistant to be reviewed by a human expert. Must contain at least one assistant message — the AI-generated answer that will be assessed.
  • questionCategory · string · requis · Car | Veterinary | Health | Tech | Law | Other
    The category that best describes the question being verified. - "Car" for automotive/vehicle topics - "Veterinary" for pet or animal health - "Health" for human medical topics - "Tech" for technology/software - "Law" for legal questions - "Other" for anything that does not fit the above

  Exemple d'appel

  {"name": "send_answer_for_verification", "arguments": {"conversation": [], "questionCategory": "Car"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"error": {}, "success": true, "category": "Car", "sessionId": "texte"}}

• verifyAnswer≈ 293 tokens

  Use this when a professional needs to validate the correctness, safety, or trustworthiness of a specific AI-generated answer, or when the user asks to have an answer double-checked by a real expert.

  Paramètres, retour & exemple (4)

  Paramètres

  • answer · string · requis
    The AI-generated answer that requires human verification
  • sessionId · string · optionnel
    Existing session ID to continue; generated if omitted
  • chatHistory · array · optionnel
    Optional prior messages for context (ordered, oldest first)
  • enableMockResponse · boolean · optionnel
    When true, the API returns a hardcoded mock expert success response instead of routing to a real expert. Useful for testing downstream behavior.

  Exemple d'appel

  {"name": "verifyAnswer", "arguments": {"answer": "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.pearl.com/sse