Combien d'outils expose io.github.SynapseLayer/synapse-layer ?

io.github.SynapseLayer/synapse-layer expose 13 outil(s). Le coût de contexte pour les charger tous est d'environ 4367 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / IA & Mémoire / io.github.SynapseLayer/synapse-layer

io.github.SynapseLayer/synapse-layer

serveur MCP (Model Context Protocol) · synapse-layer 2.4.6

▸ IA & Mémoire

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~4367 tokensCoût de contexte

13Outils

Est-ce que io.github.SynapseLayer/synapse-layer est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.SynapseLayer/synapse-layer » 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 13 outils

health_check≈ 111 tokens
Check service availability, engine version, and storage health. Public method.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "health_check", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "version": "texte", "dbLatencyMs": 1}}
```
initialize_context≈ 294 tokens
Initialize a persistent memory context for a conversation or agent session. Returns REDACTED metadata by default (detail="summary"). Use detail="full" with a reason (10–200 chars) to retrieve plaintext content under MEMORY_EXPORT_GOVERNANCE_V1.
Paramètres, retour & exemple (2)
Paramètres
- detail · string · optionnel · summary | full
  Detail level. "summary" (default) = redacted metadata only, no plaintext. "full" = plaintext content; REQUIRES the reason parameter and is audit-logged.
- reason · string · optionnel
  REQUIRED only when detail="full" (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT context. Without it, detail="full" WILL fail with code -32602.
Exemple d'appel
```
{"name": "initialize_context", "arguments": {"detail": "summary", "reason": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"scope": "agent", "agent_id": "texte", "memories": []}}
```
list_memories≈ 315 tokens
List memory metadata with pagination and governance limits.
Paramètres, retour & exemple (4)
Paramètres
- limit · number · optionnel
  Maximum memory metadata rows to return. Hard-capped: default 5, max 10. Values above 10 are silently reduced to 10.
- scope · string · optionnel · agent | tenant
  Explicit memory scope. "agent" (default, fail-closed) = lists memories for the given agent_id (or the token agent). "tenant" = lists memories across all agents of the authenticated tenant.
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
Exemple d'appel
```
{"name": "list_memories", "arguments": {"limit": 1, "scope": "agent", "subject": "texte", "agent_id": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "total": 1, "memories": []}}
```
memory_feedback≈ 288 tokens
Submit feedback to adjust trust scoring for stored memories.
Paramètres, retour & exemple (5)
Paramètres
- signal · string · requis · used | ignored | helpful | irrelevant
  Feedback signal: used (auto), helpful (positive), irrelevant (negative), ignored.
- memoryId · string · optionnel
  Deprecated camelCase alias of memory_id — still accepted for backward compatibility.
- memory_id · string · optionnel
  ID of the memory to provide feedback on (canonical snake_case name).
- sessionId · string · optionnel
  Deprecated camelCase alias of session_id — still accepted for backward compatibility.
- session_id · string · optionnel
  Optional session identifier for tracking (canonical snake_case name).
Exemple d'appel
```
{"name": "memory_feedback", "arguments": {"signal": "used"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"signal": "texte", "success": true, "memoryId": "texte"}}
```
neural_handover≈ 218 tokens
Transfer contextual state between agents with continuity controls.
Paramètres, retour & exemple (3)
Paramètres
- token · string · requis
  The handover token (64 hex chars). Generated by the source agent/user in Forge UI.
- reason · string · requis
  REQUIRED (10–200 chars). Human-readable justification for consuming this handover. Example: "Receiving project context from Claude session."
- consuming_agent · string · optionnel
  Agent identifier consuming the handover (defaults to token agent).
Exemple d'appel
```
{"name": "neural_handover", "arguments": {"token": "texte", "reason": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "handoverId": "texte"}}
```
process_text≈ 216 tokens
Extract candidate memories from free-form text with governance filters and sanitization.
Paramètres, retour & exemple (4)
Paramètres
- text · string · requis
  Free-form text to scan for auto-save triggers.
- source · string · optionnel
  Source identifier (default: mcp).
- project · string · optionnel
  Force a specific project namespace. Auto-detected if omitted.
- agent_id · string · optionnel
  Agent identifier. Defaults to "default".
Exemple d'appel
```
{"name": "process_text", "arguments": {"text": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"extracted": [], "storedCount": 1}}
```
recall≈ 585 tokens
Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.
Paramètres, retour & exemple (7)
Paramètres
- mode · string · optionnel · auto | temporal | semantic | priority | hybrid
  Recall routing mode. "temporal" = pure chronological, "semantic" = FTS + TQ ranking, "priority" = critical/high-TQ first, "hybrid" = weighted blend, "auto" = detect from query (default).
- limit · number · optionnel
  Maximum memories to return (1–50, default: 10).
- query · string · requis
  What to recall — natural language query for memory retrieval.
- scope · string · optionnel · agent | tenant
  Explicit memory scope. "agent" (default, fail-closed) = limits recall to the given agent_id (or the token agent). "tenant" = cross-agent recall within the authenticated tenant. If omitted with agent_id present, "agent" is inferred; if both omitted, the token agent is used (verified-token scope).
- reason · string · requis
  REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: "User asked me to summarize last week decisions."
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
Exemple d'appel
```
{"name": "recall", "arguments": {"query": "texte", "reason": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "scope": "agent", "memories": []}}
```
recall_memory≈ 494 tokens
Recall persisted memory by query. Alias of recall.
Paramètres, retour & exemple (7)
Paramètres
- mode · string · optionnel · auto | temporal | semantic | priority | hybrid
  Recall routing mode.
- limit · number · optionnel
  Maximum memories to return (1–50, default: 10).
- query · string · requis
  What to recall — natural language query for memory retrieval.
- scope · string · optionnel · agent | tenant
  Explicit memory scope. "agent" (default, fail-closed) = limits recall to the given agent_id (or the token agent). "tenant" = cross-agent recall within the authenticated tenant. If omitted with agent_id present, "agent" is inferred; if both omitted, the token agent is used (verified-token scope).
- reason · string · requis
  REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Without this the call WILL fail with code -32602. Example: "Checking user project status."
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
Exemple d'appel
```
{"name": "recall_memory", "arguments": {"query": "texte", "reason": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "scope": "agent", "memories": []}}
```
save_memory≈ 426 tokens
Save a memory entry to the persistent store. Alias of save_to_synapse.
Paramètres, retour & exemple (6)
Paramètres
- tags · array · optionnel
  Tags for categorization.
- content · string · requis
  The memory content to store securely.
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier for memory isolation.
- force_intent · string · optionnel
  MANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings.
- intent_reason · string · optionnel
  Auditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.
Exemple d'appel
```
{"name": "save_memory", "arguments": {"content": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "scope": "agent", "stored": true}}
```
save_to_synapse≈ 526 tokens
Persist memory with encryption at rest, sanitization, and deduplication controls.
Paramètres, retour & exemple (9)
Paramètres
- tags · array · optionnel
  Tags for categorization.
- type · string · optionnel
  Event type: [MILESTONE], [DECISION], [ALERT], [AUTO-STRAT], [AUTO-OP], [AUTO-INSIGHT], [AUTO-DECISION], [AUTO-CONTEXT], [MANUAL].
- content · string · requis
  The memory content to store securely.
- project · string · optionnel
  Project identifier (e.g., SYNAPSE_LAYER).
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier for memory isolation. Defaults to "default".
- importance · number · optionnel
  Accepted for compatibility; not enforced by the API.
- force_intent · string · optionnel
  MANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings.
- intent_reason · string · optionnel
  Auditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.
Exemple d'appel
```
{"name": "save_to_synapse", "arguments": {"content": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"status": "texte", "memory_id": "texte", "trust_quotient": 1}}
```
search≈ 463 tokens
Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content.
Paramètres, retour & exemple (6)
Paramètres
- limit · number · optionnel
  Maximum results to return (1–50, default: 20).
- query · string · requis
  Search query — natural language or keywords.
- scope · string · optionnel · agent | tenant
  Explicit search scope. "agent" (default, fail-closed) = limits search to the given agent_id (or the token agent). "tenant" = cross-agent search within the authenticated tenant. If omitted with agent_id present, "agent" is inferred; if both omitted, the token agent is used (verified-token scope).
- reason · string · requis
  REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: "Checking prior migration decisions for the user."
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
Exemple d'appel
```
{"name": "search", "arguments": {"query": "texte", "reason": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"count": 1, "scope": "agent", "results": []}}
```
slo_report≈ 189 tokens
Return uptime and SLO metrics for the MCP service.
Paramètres, retour & exemple (2)
Paramètres
- admin_token · string · requis
  Admin authentication token. Must match ADMIN_TOKEN environment variable.
- window_hours · array · optionnel
  Time windows in hours for the report. Default: [24, 168] (24h + 7d).
Exemple d'appel
```
{"name": "slo_report", "arguments": {"admin_token": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"p50": 1, "p95": 1, "uptime": 1, "window": "texte", "errorRate": 1}}
```
store_memory≈ 430 tokens
Store structured memory with metadata and trust scoring.
Paramètres, retour & exemple (6)
Paramètres
- tags · array · optionnel
  Tags for categorization.
- content · string · requis
  The memory content to store securely.
- subject · string · optionnel
  ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
- agent_id · string · optionnel
  Agent identifier for memory isolation. Defaults to "default".
- force_intent · string · optionnel
  MANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings.
- intent_reason · string · optionnel
  Auditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.
Exemple d'appel
```
{"name": "store_memory", "arguments": {"content": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "scope": "agent", "stored": true}}
```

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://forge.synapselayer.org/api/mcp