# Synapse Layer — Trust Infrastructure for AI Agents

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

- name: io.github.SynapseLayer/synapse-layer
- version: 2.4.6
- connection class: R0 (autonomous)
- trust: 93/100
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.SynapseLayer%2Fsynapse-layer
- tools: https://api.protogrid.dev/v1/servers/io.github.SynapseLayer%2Fsynapse-layer/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "synapse-layer": {
      "type": "http",
      "url": "https://forge.synapselayer.org/api/mcp",
      "headers": {
        "x-connect-token": "${X_CONNECT_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${X_CONNECT_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 98
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-95% ~updated-34d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 13 of 13 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: process_text (destructiveHint, idempotentHint); initialize_context (destructiveHint, idempotentHint); store_memory (destructiveHint); …
- pass `tools.token_cost`: about 3,474 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 1 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 13, about 3,474 tokens to load them all
- tool set hash: 1fcfd8b35d62abb9bdbf5413250ea73b
- tools last changed: 2026-10-10T11:35:10.912Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.SynapseLayer/synapse-layer.svg)](https://protogrid.dev/servers/io.github.SynapseLayer/synapse-layer)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-10 `process_text` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.SynapseLayer%2Fsynapse-layer/changes

## Remotes

- https://forge.synapselayer.org/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.9478261)

## Packages

_none_

## Tools (13)

- `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.
- `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.
- `process_text`: Extract candidate memories from free-form text with governance filters and sanitization.
- `recall`: Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.
- `recall_memory`: Recall persisted memory by query. Alias of recall.
- `save_memory`: Save a memory entry to the persistent store. Alias of save_to_synapse.
- `save_to_synapse`: Persist memory with encryption at rest, sanitization, and deduplication controls.
- `search`: Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content.
- `slo_report`: Return uptime and SLO metrics for the MCP service.
- `store_memory`: Store structured memory with metadata and trust scoring.