# Synapse Layer — Trust Infrastructure for AI Agents (remote · forge.synapselayer.org)

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

- Trust score: 58/100 (low)
- Change this week: −3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `forge.synapselayer.org`: 58/100 (this document), [markdown](https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp.md), [page](https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp)
- pypi · `synapse-layer`: 21/100, [markdown](https://verifymcp.io/servers/synapselayer-synapse-layer/synapse-layer.md), [page](https://verifymcp.io/servers/synapselayer-synapse-layer/synapse-layer)

## Channel facts

- Endpoint: `https://forge.synapselayer.org/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.4.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 33/100
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 2156 tokens (~165/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http synapselayer-synapse-layer https://forge.synapselayer.org/api/mcp
```

### Codex

```toml
[mcp_servers.synapselayer-synapse-layer]
url = "https://forge.synapselayer.org/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "synapselayer-synapse-layer": {
      "type": "remote",
      "url": "https://forge.synapselayer.org/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add synapselayer-synapse-layer --url https://forge.synapselayer.org/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  synapselayer-synapse-layer:
    url: "https://forge.synapselayer.org/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "synapselayer-synapse-layer": {
      "type": "http",
      "url": "https://forge.synapselayer.org/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 57, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 54, −7)

- [functional regression] Schema quality: 112 → 165
- [functional] Schema quality: good → poor

### 2026-07-27 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 60)

First indexed and scored.

## MCP tools (13)

### `recall` (~292 tokens)

Retrieve relevant persisted memory using semantic, temporal, priority, or hybrid routing. Governance: requires reason (10–200 chars). Rate limit: 20/min.

Input parameters:

- `agent_id` (string): Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
- `limit` (number): Maximum memories to return (1–50, default: 10).
- `mode` (string): Recall routing mode. "temporal" = pure chronological, "semantic" = FTS + TQ ranking, "priority" = critical/high-TQ first, "hybrid" = weighted blend, "auto" = detect from query (default).
- `query` (string, required): What to recall — natural language query for memory retrieval.
- `reason` (string, required): REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example:…
- `scope` (string): Explicit memory scope. "agent" (default, fail-closed) = limits recall to the given agent_id (or the token agent). "tenant" = cross-agent recall within the authenticated tenant. If omitted with agent_…

### `save_to_synapse` (~158 tokens)

Persist memory with encryption at rest, sanitization, and deduplication controls.

Input parameters:

- `agent_id` (string): Agent identifier for memory isolation. Defaults to "default".
- `content` (string, required): The memory content to store securely.
- `importance` (number): Importance level 1–5 (default: 3).
- `project` (string): Project identifier (e.g., SYNAPSE_LAYER).
- `tags` (array): Tags for categorization.
- `type` (string): Event type: [MILESTONE], [DECISION], [ALERT], [AUTO-STRAT], [AUTO-OP], [AUTO-INSIGHT], [AUTO-DECISION], [AUTO-CONTEXT], [MANUAL].

### `process_text` (~95 tokens)

Extract candidate memories from free-form text with governance filters and sanitization.

Input parameters:

- `agent_id` (string): Agent identifier. Defaults to "default".
- `project` (string): Force a specific project (e.g., SYNAPSE_LAYER, OFFLY). Auto-detected if omitted.
- `source` (string): Source identifier (default: mcp).
- `text` (string, required): Free-form text to scan for auto-save triggers.

### `search` (~151 tokens)

Search persisted memory across agent scopes using full-text matching.

Input parameters:

- `agent_id` (string): Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
- `limit` (number): Maximum results to return (1–50, default: 20).
- `query` (string, required): Search query — natural language or keywords.
- `scope` (string): Explicit search scope. "agent" (default, fail-closed) = limits search to the given agent_id (or the token agent). "tenant" = cross-agent search within the authenticated tenant. If omitted with agent_…

### `health_check` (~22 tokens)

Check service availability, engine version, and storage health. Public method.

### `initialize_context` (~20 tokens)

Initialize a persistent memory context for a conversation or agent session.

### `save_memory` (~61 tokens)

Save a memory entry to the persistent store. Alias of save_to_synapse.

Input parameters:

- `agent_id` (string): Agent identifier for memory isolation.
- `content` (string, required): The memory content to store securely.
- `tags` (array): Tags for categorization.

### `store_memory` (~59 tokens)

Store structured memory with metadata and trust scoring.

Input parameters:

- `agent_id` (string): Agent identifier for memory isolation. Defaults to "default".
- `content` (string, required): The memory content to store securely.
- `tags` (array): Tags for categorization.

### `recall_memory` (~209 tokens)

Recall persisted memory by query. Alias of recall.

Input parameters:

- `agent_id` (string): Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
- `limit` (number): Maximum memories to return (1–50, default: 10).
- `mode` (string): Recall routing mode.
- `query` (string, required): What to recall — natural language query for memory retrieval.
- `reason` (string, required): REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Without this the call WILL fail with code -32602. Example: "Checking user project status."
- `scope` (string): Explicit memory scope. "agent" (default, fail-closed) = limits recall to the given agent_id (or the token agent). "tenant" = cross-agent recall within the authenticated tenant. If omitted with agent_…

### `list_memories` (~128 tokens)

List memory metadata with pagination and governance limits.

Input parameters:

- `agent_id` (string): Agent identifier (canonical or alias). Used only when scope="agent" or scope is inferred.
- `limit` (number): Maximum memory metadata rows to return. Hard-capped: default 5, max 10. Values above 10 are silently reduced to 10.
- `scope` (string): Explicit memory scope. "agent" (default, fail-closed) = lists memories for the given agent_id (or the token agent). "tenant" = lists memories across all agents of the authenticated tenant.

### `memory_feedback` (~70 tokens)

Submit feedback to adjust trust scoring for stored memories.

Input parameters:

- `memoryId` (string, required): ID of the memory to provide feedback on.
- `sessionId` (string): Optional session identifier for tracking.
- `signal` (string, required): Feedback signal: used (auto), helpful (positive), irrelevant (negative), ignored.

### `neural_handover` (~95 tokens)

Transfer contextual state between agents with continuity controls.

Input parameters:

- `consuming_agent` (string): Agent identifier consuming the handover (defaults to token agent).
- `reason` (string, required): REQUIRED (10–200 chars). Human-readable justification for consuming this handover. Example: "Receiving project context from Claude session."
- `token` (string, required): The handover token (64 hex chars). Generated by the source agent/user in Forge UI.

### `slo_report` (~68 tokens)

Return uptime and SLO metrics for the MCP service.

Input parameters:

- `admin_token` (string, required): Admin authentication token. Must match ADMIN_TOKEN environment variable.
- `window_hours` (array): Time windows in hours for the report. Default: [24, 168] (24h + 7d).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp#diagnostics

## Score history

- 2026-08-03: 58
- 2026-08-02: 58
- 2026-08-01: 57
- 2026-07-31: 57
- 2026-07-30: 55
- 2026-07-29: 55
- 2026-07-28: 54
- 2026-07-27: 61
- 2026-07-26: 60

## Links

- Remote endpoint: https://forge.synapselayer.org/api/mcp
- Repository: https://github.com/SynapseLayer/synapse-layer
- Website: https://synapselayer.org/
- Changelog RSS feed: https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/synapselayer-synapse-layer/api-mcp