MCP Overview
Synapse Layer implements the Model Context Protocol (MCP) standard, exposing 13 tools for persistent, encrypted memory operations. Any MCP-compatible client can connect.
On this page
What is MCP?
The Model Context Protocol (MCP) is an open standard that enables AI models and agents to interact with external tools and data sources through a unified interface. Instead of building custom integrations for each AI platform, MCP provides a single protocol that works across Claude, Cursor, and any MCP-compatible client.
Synapse Layer is a first-class MCP server — listed on the official MCP Registry, Smithery, and Glama.
Synapse Layer as MCP Server
When an AI agent connects to Synapse Layer via MCP, it gains access to persistent, encrypted memory that survives across sessions, models, and tools. Every memory operation passes through the 3-layer security pipeline:
- ▸Semantic Privacy Guard™ — PII detection and redaction
- ▸Differential Privacy — Gaussian noise on embeddings
- ▸Intelligent Intent Validation™ — intent classification and confidence gating
Content is encrypted at rest with AES-256-GCM. Each tenant is fully isolated.
Transport Options
| Transport | URL / Command | Best For |
|---|---|---|
| Streamable HTTP | https://forge.synapselayer.org/api/mcp | Remote clients, web apps, no local install |
| stdio | uvx synapse-layer | Claude Desktop, Cursor, local MCP hosts |
Tool Categories
13 tools organized into 5 categories:
Memory Operations (5)
store_memory/save_memory/save_to_synapserecall_memory/recall
Search & List (2)
searchlist_memories
Processing (1)
process_text— extract and auto-save memories from free-form text
Feedback & Governance (2)
memory_feedbackneural_handover(beta)
System (3)
health_checkinitialize_contextslo_report(admin only)
Registry Listings
Synapse Layer is listed on multiple MCP registries:
- ▸Official MCP Registry —
io.github.SynapseLayer/synapse-layer - ▸Smithery —
@synapselayer/synapse-protocol - ▸Glama —
synapse-layer