Synapse Layer — Trust Infrastructure for AI Agents
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
| Endpoint | https://forge.synapselayer.org/api/mcp (streamable-http) |
|---|---|
| Registry version | 2.4.6 |
| Now | 13 tools · grade C (75) · pin ts_9ad9c90db06a4a26c81a9704877cc1e8 · protocol 2025-11-25 |
| First / last listed | 2026-10-28 02:32 UTC / 2026-10-28 02:32 UTC |
| Grade over time | 2026-10-28: C (75), 13 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: recall save_to_synapse process_text search health_check initialize_context save_memory store_memory recall_memory list_memories memory_feedback neural_handover slo_report
recall | Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min. params: query*, reason*, scope, agent_id, limit, mode, subject |
save_to_synapse | Persist memory with encryption at rest, sanitization, and deduplication controls. params: content*, agent_id, project, type, importance, tags, force_intent, intent_reason, subject |
process_text | Extract candidate memories from free-form text with governance filters and sanitization. params: text*, agent_id, project, source |
search | Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content. params: query*, reason*, scope, agent_id, limit, subject |
health_check | Check service availability, engine version, and storage health. Public method. params: none |
initialize_context | 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. params: detail, reason |
save_memory | Save a memory entry to the persistent store. Alias of save_to_synapse. params: content*, agent_id, tags, force_intent, intent_reason, subject |
store_memory | Store structured memory with metadata and trust scoring. params: content*, agent_id, tags, force_intent, intent_reason, subject |
recall_memory | Recall persisted memory by query. Alias of recall. params: query*, reason*, scope, agent_id, limit, mode, subject |
list_memories | List memory metadata with pagination and governance limits. params: scope, agent_id, limit, subject |
memory_feedback | Submit feedback to adjust trust scoring for stored memories. params: memory_id, memoryId, signal*, session_id, sessionId |
neural_handover | Transfer contextual state between agents with continuity controls. params: token*, reason*, consuming_agent |
slo_report | Return uptime and SLO metrics for the MCP service. params: admin_token*, window_hours |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.