dev.gnosem/gnosem

Est-ce que dev.gnosem/gnosem est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.gnosem/gnosem » 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 6 outils

• memory_forget≈ 78 tokens

  Soft-delete a memory by id. The row is retained for audit but excluded from search/list and removed from the vector index.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    UUID of the memory to forget.

  Exemple d'appel

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

  Exemple de retour

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

• memory_list≈ 337 tokens

  List the user's most recent memories in reverse chronological order. Use for browsing or catching up on what the user's other model sessions have written recently. Same content/content_raw shape as memory_search. Optional filters (tags, written_by, session_id, since, until) narrow the listing at the SQL level.

  Paramètres, retour & exemple (8)

  Paramètres

  • raw · boolean · optionnel
    Return original prose instead of the compressed form. Default false.
  • tags · array · optionnel
    Only return memories containing ALL of these tags (AND semantics).
  • limit · integer · optionnel
    Max rows to return (1–200). Default 50.
  • since · integer · optionnel
    Only return memories created at or after this ms-epoch timestamp.
  • until · integer · optionnel
    Only return memories created strictly before this ms-epoch timestamp.
  • cursor · integer · optionnel
    Pagination cursor from a previous call's `cursor` field (ms epoch); returns rows older than this timestamp.
  • session_id · string · optionnel
    Only return memories with an exact session_id match.
  • written_by · string · optionnel
    Only return memories with an exact written_by match.

  Exemple d'appel

  {"name": "memory_list", "arguments": {"raw": true, "tags": [], "limit": 1, "since": 1, "until": 1, "cursor": 1}}

  Exemple de retour

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

• memory_search≈ 435 tokens

  Search the user's memories. Default mode is 'hybrid': blends semantic (cosine over Vectorize) and keyword (BM25 over SQLite FTS5) hits via Reciprocal Rank Fusion (k=60). Semantic catches paraphrases; keyword catches exact-string hits (IDs, dates, code snippets). Pass mode:'semantic' or mode:'keyword' to run just one. Content defaults to the LLM-optimized (compressed) form when available (raw:true to invert). Excludes forgotten + superseded. Optional filters narrow after retrieval: tags (AND), written_by, session_id, and/or since/until (ms epoch).

  Paramètres, retour & exemple (9)

  Paramètres

  • k · integer · optionnel
    Max results (1–50). Default 10.
  • raw · boolean · optionnel
    Return original prose instead of the compressed form. Default false.
  • mode · string · optionnel · semantic | keyword | hybrid
    Retrieval mode. Default 'hybrid'.
  • tags · array · optionnel
    Only return memories containing ALL of these tags (AND semantics).
  • query · string · requis
    Search query. Interpreted as natural language for semantic mode and as FTS5-safe text for keyword mode.
  • since · integer · optionnel
    Only return memories created at or after this ms-epoch timestamp.
  • until · integer · optionnel
    Only return memories created strictly before this ms-epoch timestamp.
  • session_id · string · optionnel
    Only return memories with an exact session_id match.
  • written_by · string · optionnel
    Only return memories with an exact written_by match (e.g. 'claude-code').

  Exemple d'appel

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

  Exemple de retour

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

• memory_supersede≈ 162 tokens

  Replace a stale memory with a corrected one. The old row is marked superseded and excluded from future reads; the new row becomes the current version. Use for corrections; use memory_forget for pure deletions.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • old_id · string · requis
    UUID of the memory to replace.
  • session_id · string · optionnel
  • written_by · string · optionnel
  • new_content · string · requis
    New content that supersedes the old memory.

  Exemple d'appel

  {"name": "memory_supersede", "arguments": {"old_id": "texte", "new_content": "texte"}}

  Exemple de retour

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

• memory_write≈ 402 tokens

  Save a fact, preference, decision, or note to the user's cross-model memory. Any MCP client can read this back later. Include written_by (e.g. 'claude-code', 'gpt-5', 'kimi-k2') for provenance and session_id to group related writes. Long content (>400 chars) is automatically compressed on write to a structured-facts form optimized for LLM reading — the raw text is preserved. Pass no_optimize:true to skip. Writes are deduped by default: (1) SHA-256 of trim(content) short-circuits byte-identical writes with { id, exact_duplicate:true } for free (no embed call); (2) failing that, semantic dedup returns { id, deduped:true, matched_score } when cosine ≥ 0.85. Pass force:true to bypass both, or use memory_supersede to explicitly correct a prior memory.

  Paramètres, retour & exemple (6)

  Paramètres

  • tags · array · optionnel
    Optional short labels for filtering (e.g. ['preference','stack']).
  • force · boolean · optionnel
    Bypass semantic dedup and write anyway. Default false.
  • content · string · requis
    The fact or note to remember. Plain text, max 8000 characters.
  • session_id · string · optionnel
    Opaque identifier grouping related writes from the same conversation.
  • written_by · string · optionnel
    Identifier of the model / client writing this (e.g. 'claude-code', 'gpt-5', 'kimi-k2', 'manual').
  • no_optimize · boolean · optionnel
    Skip AI compression of long content. Default false.

  Exemple d'appel

  {"name": "memory_write", "arguments": {"content": "texte"}}

  Exemple de retour

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

• memory_write_bulk≈ 326 tokens

  Write up to 50 memories in a single call. Each entry runs the same path as memory_write (semantic dedup by default; pass force:true per-entry to skip). Embeddings + optimizations run in parallel; D1 inserts are batched. Returns { results: [...] } with one entry per input in the same order — each is { id, created_at, optimized? } on success, { id, created_at, deduped, matched_score } on dedup, or { error } on failure. Free-tier limits apply to the sum: if adding N would exceed 200, the first (200 - existing) succeed and the rest return an error.

  Paramètres, retour & exemple (1)

  Paramètres

  • memories · array · requis
    Array of memory-write entries (1–50).

  Exemple d'appel

  {"name": "memory_write_bulk", "arguments": {"memories": []}}

  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://gnosem.dev/mcp