ai.workingmemory/memory

Est-ce que ai.workingmemory/memory est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.workingmemory/memory » 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

• capture_memory≈ 309 tokens

  Capture durable facts from a task you just completed (drafting an email, summarizing a document, making a decision), as a byproduct — the user does nothing. Pass the task output/content; durable facts are extracted and stored automatically. Always include your conversation id in client.conversation_id. Returns immediately; extraction happens in the background.

  Paramètres, retour & exemple (3)

  Paramètres

  • client · object · optionnel
    Current client session context. Pass your conversation/thread id as conversation_id.
  • task_content · string · requis
    The task output/content to mine for durable facts (max 32KB).
  • task_description · string · optionnel
    Optional one-line description of the task, as extraction framing.

  Exemple d'appel

  {"name": "capture_memory", "arguments": {"task_content": "texte"}}

  Exemple de retour

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

• manage_memory≈ 149 tokens

  Manage an existing memory item. Currently supports deleting a memory by id (soft delete — recoverable for 30 days). Use search_memory to find the id first.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    The memory item id to act on.
  • action · string · requis · delete
    The management action to perform.

  Exemple d'appel

  {"name": "manage_memory", "arguments": {"id": "texte", "action": "delete"}}

  Exemple de retour

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

• save_memory≈ 310 tokens

  Save a thought, insight, fact, or todo to the user's Working Memory. The text is parsed and stored as one or more structured memory items, searchable a moment later via search_memory. Also use this when the user pastes memories or notes brought from another assistant — pass the full pasted text; it is split into individual memories automatically.

  Paramètres, retour & exemple (2)

  Paramètres

  • text · string · requis
    The thought or note to save.
  • client · object · optionnel
    Optional context about the originating client session. Helps users later find saves from a specific conversation. `conversation_id` groups multiple saves; `conversation_title` is human-readable.

  Exemple d'appel

  {"name": "save_memory", "arguments": {"text": "texte"}}

  Exemple de retour

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

• search_memory≈ 413 tokens

  Search the user's Working Memory for relevant past notes and facts. Use this when the user references something they may have stored earlier, or to find related context before answering. Always include your conversation id in client.conversation_id.

  Paramètres, retour & exemple (5)

  Paramètres

  • k · number · optionnel
    Max results (1–20). Defaults to a sensible value.
  • query · string · requis
    Semantic query.
  • client · object · optionnel
    Context about the CURRENT client session. Pass your conversation/thread id as `conversation_id` — it identifies this session for cross-session memory instrumentation and does NOT filter results (use the top-level `conversation_id` parameter for filtering).
  • dedupe_recent · boolean · optionnel
    Optional. When false, semantic matches that are also recent are still returned in `relevant` (raw semantic results rather than RAG-deduped). Defaults to true.
  • conversation_id · string · optionnel
    Optional. Restrict results to notes stamped with this conversation_id at save_memory time. Empty / whitespace-only values are treated as absent.

  Exemple d'appel

  {"name": "search_memory", "arguments": {"query": "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://app.workingmemory.ai/mcp