mcp server
Synapse Layer — Trust Infrastructure for AI Agents
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Description as published by the maintainer. Source
- version 2.4.4
- active
- memory and context
active — Registry entry last updated 2026-07-02. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
13 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
health_check- Check service availability, engine version, and storage health. Public method.
initialize_context- Initialize a persistent memory context for a conversation or agent session.
list_memories(limit, scope, agent_id)- List memory metadata with pagination and governance limits.
memory_feedback(signal, memoryId, sessionId)- Submit feedback to adjust trust scoring for stored memories. Required: memoryId, signal.
neural_handover(token, reason, consuming_agent)- Transfer contextual state between agents with continuity controls. Required: token, reason.
process_text(text, source, project, agent_id)- Extract candidate memories from free-form text with governance filters and sanitization. Required: text.
recall(mode, limit, query, scope, reason, agent_id)- Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min. Required: query, reason.
recall_memory(mode, limit, query, scope, reason, agent_id)- Recall persisted memory by query. Alias of recall. Required: query, reason.
save_memory(tags, content, agent_id)- Save a memory entry to the persistent store. Alias of save_to_synapse. Required: content.
save_to_synapse(tags, type, content, project, agent_id, importance)- Persist memory with encryption at rest, sanitization, and deduplication controls. Required: content.
search(limit, query, scope, agent_id)- Search persisted memory across agent scopes using full-text matching. Required: query.
slo_report(admin_token, window_hours)- Return uptime and SLO metrics for the MCP service. Required: admin_token.
store_memory(tags, content, agent_id)- Store structured memory with metadata and trust scoring. Required: content.
Last successful function declaration observed on . Source: https://forge.synapselayer.org/api/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://forge.synapselayer.org/api/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 2.4.4 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-02 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-02 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 13 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | forge.synapselayer.org | |
| mcp endpoint status | ok | The server listed 13 functions when asked. | as of probe | forge.synapselayer.org |
Where to get it
Also from synapselayer
-
Synapse Layer — Zero-Knowledge Memory
Zero-Knowledge Context™ & Neural Handover™ for AI Agents. The Trust Layer for AI Memory.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json