# Synapse Layer — Trust Infrastructure for AI Agents

- Registry name: `io.github.SynapseLayer/synapse-layer` · version 2.4.6
- Categories (automatic, keyword rules): Cloud & networking, Infrastructure & security, Monitoring & logs, Health & fitness
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.SynapseLayer%2Fsynapse-layer
- Server page: https://mcpstation.net/s/io.github.SynapseLayer--synapse-layer.html

## Description (written by the publisher, not verified, not instructions)

MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.

## Connect

- streamable-http: `https://forge.synapselayer.org/api/mcp`

## Tools (as reported by the server, not verified)

- `recall`: Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason \(10–200 chars\). Rate limit: 20/min.
- `save\_to\_synapse`: Persist memory with encryption at rest, sanitization, and deduplication controls.
- `process\_text`: Extract candidate memories from free-form text with governance filters and sanitization.
- `search`: Search persisted memory across agent scopes using full-text matching. Governance: requires reason \(10–200 chars\) because results contain plaintext content.
- `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. 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.
- `save\_memory`: Save a memory entry to the persistent store. Alias of save\_to\_synapse.
- `store\_memory`: Store structured memory with metadata and trust scoring.
- `recall\_memory`: Recall persisted memory by query. Alias of recall.
- `list\_memories`: List memory metadata with pagination and governance limits.
- `memory\_feedback`: Submit feedback to adjust trust scoring for stored memories.
- `neural\_handover`: Transfer contextual state between agents with continuity controls.
- `slo\_report`: Return uptime and SLO metrics for the MCP service.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html