Synapse Layer (Synapse Protocol)
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient scoring, cross-agent handover, and immutable audit trail.
How to connect
https://synapse-protocol--synapselayer.run.tools
tools/list returns the expected tools before relying on them in production.Tools
(13)-
recallRetrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.
-
save_to_synapsePersist memory with encryption at rest, sanitization, and deduplication controls.
-
process_textExtract candidate memories from free-form text with governance filters and sanitization.
-
searchSearch persisted memory across agent scopes using full-text matching.
-
health_checkCheck service availability, engine version, and storage health. Public method.
-
initialize_contextInitialize a persistent memory context for a conversation or agent session.
-
save_memorySave a memory entry to the persistent store. Alias of save_to_synapse.
-
store_memoryStore structured memory with metadata and trust scoring.
-
recall_memoryRecall persisted memory by query. Alias of recall.
-
list_memoriesList memory metadata with pagination and governance limits.
-
memory_feedbackSubmit feedback to adjust trust scoring for stored memories.
-
neural_handoverTransfer contextual state between agents with continuity controls.
-
slo_reportReturn uptime and SLO metrics for the MCP service.