Provides persistent, AES-256-GCM encrypted memory infrastructure for AI agents to enable cross-session and cross-agent context recall.
Also known as SynapseLayer/synapse-layer, synapse-secure-memory, synapse-layer
- Stars
- 13
- Tools
- 13
- Downloads, 30 days
- 212
- Latest version
- 1.0.7
- Last commit
- Nov 4, 2026
- License
- Apache-2.0
What is Synapse Layer MCP?
Synapse Layer provides persistent, AES-256-GCM encrypted memory infrastructure for AI agents to enable cross-session and cross-agent context recall. It exposes 13 tools, such as recall, save_to_synapse, process_text.
Summary generated from the project's README
About Synapse Layer MCP server
Synapse Layer provides a persistent memory infrastructure designed to give AI agents continuity across different sessions and models. It functions as a specialized storage layer that prevents agents from forgetting context once a conversation ends. Developers can integrate this service into MCP-compatible clients like Claude Desktop, Cursor, or any tool running via npx using the mcp-remote bridge. The system uses AES-256-GCM encryption at rest to ensure data security and employs pgvector HNSW for semantic search capabilities.
To use the service, developers must obtain a connect token from the Forge dashboard and provide it via the x-connect-token header. The server exposes 13 specific tools, including recall, save_memory, and search, to manage memory workflows. This setup allows for cross-agent continuity, meaning information saved in one environment like ChatGPT can be retrieved later in another like Claude. It is built for anyone needing to move beyond stateless LLM interactions toward long-term, secure, and searchable agent memory.
What you can do with it
- 1Maintain long-term assistant memoryAn AI assistant can remember specific user preferences and past decisions across multiple different sessions.
- 2Enable cross-agent context sharingA developer can save context within one AI agent and then recall that same information using a different agent.
- 3Secure memory for MCP clientsUsers can connect tools like Cursor or Claude Desktop to a governed and encrypted memory layer.
- 4Implement semantic recall for agentsAgents can use semantic search to find relevant past information based on the meaning of a query.
Written from the project's README. Every use case is checked against a quote from it.
How to install Synapse Layer MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Synapse Layer MCP in Claude Code
$ claude mcp add --env 'SYNAPSE_ENCRYPTION_KEY=<YOUR_SYNAPSE_ENCRYPTION_KEY>' synapse-secure-memory -- uvx synapse-layerInstall Synapse Layer MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"synapse-secure-memory": {
"command": "uvx",
"args": [
"synapse-layer"
],
"env": {
"SYNAPSE_ENCRYPTION_KEY": "<YOUR_SYNAPSE_ENCRYPTION_KEY>"
}
}
}
}Install Synapse Layer MCP in VS Code
.vscode/mcp.json
{
"servers": {
"synapse-secure-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"synapse-layer"
],
"env": {
"SYNAPSE_ENCRYPTION_KEY": "<YOUR_SYNAPSE_ENCRYPTION_KEY>"
}
}
}
}Install Synapse Layer MCP in VS Code CLI
$ code --add-mcp '{"name":"synapse-secure-memory","type":"stdio","command":"uvx","args":["synapse-layer"],"env":{"SYNAPSE_ENCRYPTION_KEY":"<YOUR_SYNAPSE_ENCRYPTION_KEY>"}}'Install Synapse Layer MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"synapse-secure-memory": {
"command": "uvx",
"args": [
"synapse-layer"
],
"env": {
"SYNAPSE_ENCRYPTION_KEY": "<YOUR_SYNAPSE_ENCRYPTION_KEY>"
}
}
}
}Install Synapse Layer MCP in Codex
$ codex mcp add synapse-secure-memory --env 'SYNAPSE_ENCRYPTION_KEY=<YOUR_SYNAPSE_ENCRYPTION_KEY>' -- uvx synapse-layerInstall Synapse Layer MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.synapse-secure-memory] command = "uvx" args = ["synapse-layer"] [mcp_servers.synapse-secure-memory.env] SYNAPSE_ENCRYPTION_KEY = "<YOUR_SYNAPSE_ENCRYPTION_KEY>"
Install Synapse Layer MCP in Gemini CLI
$ gemini mcp add -s user -e 'SYNAPSE_ENCRYPTION_KEY=<YOUR_SYNAPSE_ENCRYPTION_KEY>' synapse-secure-memory uvx -- synapse-layerInstall Synapse Layer MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"synapse-secure-memory": {
"command": "uvx",
"args": [
"synapse-layer"
],
"env": {
"SYNAPSE_ENCRYPTION_KEY": "<YOUR_SYNAPSE_ENCRYPTION_KEY>"
}
}
}
}Synapse Layer MCP tools 13
Detected from the READMErecallsave_to_synapseprocess_textsearchhealth_checkinitialize_contextsave_memorystore_memoryrecall_memorylist_memoriesmemory_feedbackneural_handover
| recall | — | |
| save_to_synapse | — | |
| process_text | — | |
| search | — | |
| health_check | — | |
| initialize_context | — | |
| save_memory | — | |
| store_memory | — | |
| recall_memory | — | |
| list_memories | — | |
| memory_feedback | — | |
| neural_handover | — |
Show all 13 toolsShow fewer tools
slo_report
| slo_report | — |
Configuration
SYNAPSE_ENCRYPTION_KEYSecretAES-256-GCM encryption key for at-rest memory encryption. Auto-generated if not provided.
LOG_LEVELLogging verbosity: DEBUG, INFO, WARNING, ERROR. Default: INFO.
SYNAPSE_AGENT_IDIdentifier for the agent using the memory layer (e.g., claude-desktop, my-agent).
SYNAPSE_PRIVACY_EPSILONDifferential privacy epsilon parameter. Lower values = stronger privacy. Range: 0.1–2.0.
| Name | Description | |
|---|---|---|
| SYNAPSE_ENCRYPTION_KEY | AES-256-GCM encryption key for at-rest memory encryption. Auto-generated if not provided. | Secret |
| LOG_LEVEL | Logging verbosity: DEBUG, INFO, WARNING, ERROR. Default: INFO. | |
| SYNAPSE_AGENT_ID | Identifier for the agent using the memory layer (e.g., claude-desktop, my-agent). | |
| SYNAPSE_PRIVACY_EPSILON | Differential privacy epsilon parameter. Lower values = stronger privacy. Range: 0.1–2.0. |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHub🧠 Synapse Layer
RAG retrieves. Synapse remembers.
Persistent memory infrastructure for AI agents — AES-256-GCM encrypted at rest, semantic search, MCP-native.
Synapse Layer is open-source persistent memory infrastructure for AI agents and assistants. Memories are encrypted at rest with AES-256-GCM, indexed via pgvector HNSW for semantic recall, and exposed through MCP JSON-RPC for native integration with Claude, GPT, Gemini, and any MCP-compatible client. Apache 2.0 licensed.
Status and limits: see FEATURES.md — the public contract for what is shipped, gated, experimental or roadmap.
⚡ 30-Second Quickstart
Get your Connect Token at forge.synapselayer.org → Connect, then add the MCP endpoint to your client:
claude mcp add --transport http synapse-layer \
https://forge.synapselayer.org/api/mcp \
--header "x-connect-token: sk_connect_YOUR_TOKEN"
For Claude Desktop, Cursor and other clients, use the npx mcp-remote block under MCP Integration. Smithery's proxy/CLI was retired on 31 Oct 2026; the direct endpoint above is canonical.
Or use the Python SDK:
from synapse_layer import Synapse
s = Synapse(token="sk_connect_YOUR_TOKEN")
s.store("user likes coffee")
print(s.recall("what does user like?"))
Get your token at forge.synapselayer.org → Dashboard → Connect
What is Synapse Layer?
The persistent memory layer for AI agents — the missing piece between stateless LLMs and real continuity of context.
Your AI agents forget everything between sessions. Synapse Layer fixes that.
| Feature | Description |
|---|---|
| 🔐 Encrypted at rest | AES-256-GCM with per-operation random IV and HMAC-SHA-256 integrity |
| 🧩 One-click connect | Claude Desktop, Cursor, LangChain, CrewAI, n8n |
| 🌐 Cross-agent memory | Save in ChatGPT, recall in Claude |
| ⚡ MCP-native | Any MCP-compatible agent |
| 🔒 Header-first auth | Tokens never in URLs or logs |
| 🎯 Trust Quotient | Trust-weighted recall — confidence, recency and usage combined with semantic relevance |
Why Synapse Layer?
Your AI agents forget everything between sessions. Synapse Layer fixes that — in one line.
| Without Synapse Layer | With Synapse Layer |
|---|---|
| Agent forgets context every session | Persistent memory across all sessions |
| Memory locked to one model | Cross-agent: save in ChatGPT, recall in Claude |
| No audit trail | Append-only audit events for scope changes and curation decisions |
| Complex integration | pip install synapse-layer + 3 lines of code |
| Plaintext stored on servers | AES-256-GCM encrypted at rest |
Use Cases
- Long-term assistant memory — persist user preferences, facts, and prior decisions across sessions.
- Cross-agent continuity — save context in one agent and recall it in another.
- Secure memory for MCP clients — connect Claude Desktop, Cursor, and other MCP-compatible tools to a governed memory layer.
- Operational memory for teams — maintain structured context, trust scoring, and searchable recall for production agents.
Install
pip install synapse-layer
Quick Start
Python Script
from synapse_layer import Synapse
client = Synapse(token="sk_connect_YOUR_TOKEN")
# Store
client.store("User prefers dark mode and concise answers")
# Recall
results = client.recall("user preferences")
for r in results:
print(r["content"], r["trust_quotient"])
With Context Manager
from synapse_layer import Synapse
with Synapse(token="sk_connect_YOUR_TOKEN") as client:
client.store("User prefers dark mode and concise answers")
results = client.recall("user preferences")
for r in results:
print(r["content"])
Get your token at forge.synapselayer.org → Dashboard → Connect
13 MCP Tool Names at a Glance
Synapse Layer registers 13 public tool names (10 operations plus 3 aliases) for persistent memory workflows:
recallsave_to_synapseprocess_textsearchhealth_checkinitialize_contextsave_memorystore_memoryrecall_memorylist_memoriesmemory_feedbackneural_handoverslo_report
save_memory, store_memory and save_to_synapse are aliases; recall and recall_memory are aliases. These tools cover memory capture, semantic recall, structured storage, feedback loops, agent handoff, and operational observability.
Deployment Modes
The public package runs the client and local engine. The hosted Forge adds corporate organizations, projects, memberships, curation policies and audit. See FEATURES.md for what is OSS, hosted, gated or roadmap.
Python Script Mode
Use the SDK when you want direct Python access to Forge memory from your application.
Best for:
- prototypes and scripts
- Python-native workflows
- fast integration into existing apps
Cloud / Forge API
Use Forge when you need persistent, cross-session, and cross-agent memory with managed access tokens.
Best for:
- production assistants
- multi-agent systems
- MCP-based integrations
- shared memory across tools and sessions
MCP Integration (one tested path per client)
Claude Code (CLI)
claude mcp add --transport http synapse-layer \
https://forge.synapselayer.org/api/mcp \
--header "x-connect-token: sk_connect_YOUR_TOKEN"
The URL is a positional argument — claude mcp add --transport http <name> <url> — there is no --url flag.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"synapse-layer": {
"command": "npx",
"args": [
"mcp-remote",
"https://forge.synapselayer.org/api/mcp",
"--header",
"x-connect-token: sk_connect_YOUR_TOKEN"
]
}
}
}
Cursor
Add to .cursor/mcp.json in your project root (same JSON block as above).
Any MCP client
Any host that runs npx can use the mcp-remote block above unchanged — it bridges local stdio to the remote endpoint.
Config file locations:
- Claude Desktop — macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Claude Desktop — Windows:
%APPDATA%\Claude\claude_desktop_config.json - Claude Desktop — Linux:
~/.config/Claude/claude_desktop_config.json
API — Header-First Auth
# Health check
curl -H "x-connect-token: sk_connect_YOUR_TOKEN" \
https://forge.synapselayer.org/api/connect/health
# Save memory
curl -X POST \
-H "x-connect-token: sk_connect_YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"content": "User is a Python developer"}' \
https://forge.synapselayer.org/api/v1/capture
Security
| Feature | Implementation |
|---|---|
| Encryption | AES-256-GCM at rest with per-operation random IV |
| Integrity | HMAC-SHA-256 on content |
| Auth | Header-first (x-connect-token) — tokens never in URLs or logs |
| Privacy | Content sanitization + tenant-scoped encrypted storage |
| Isolation | Personal: 1 user = 1 private mind. Corporate: organization → projects → memberships, with tenant-scoped queries |
See SECURITY.md for vulnerability reporting.
Related Projects
| Project | Description |
|---|---|
| synapse-sdk-python | Python SDK — LangChain, CrewAI, and A2A protocol adapters |
| synapse-layer-skill | MCP skill configuration for Claude Desktop, Cursor, Windsurf |
| synapse-layer-langgraph | LangGraph checkpoint saver with encrypted state persistence |
Governance
- Public features and limits follow FEATURES.md.
- Internal governance follows the Public Claims Matrix.
- Architecture details that reveal benefits are public; mechanisms that enable them are private.
- Claim = Reality. If it's not implemented, it's not in the README.
License
Apache-2.0 © Synapse Layer
Synapse Layer MCP questions
How do I add Synapse Layer MCP to Claude Code?
Run claude mcp add --env 'SYNAPSE_ENCRYPTION_KEY=<YOUR_SYNAPSE_ENCRYPTION_KEY>' synapse-secure-memory -- uvx synapse-layer in your terminal. Add --scope user to make it available in every project.
How do I add Synapse Layer MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Synapse Layer MCP provide?
It exposes 13 tools, including recall, save_to_synapse, process_text, search, health_check.
How is the memory secured?
Memories are encrypted at rest using AES-256-GCM with per-operation random IV and HMAC-SHA-256 integrity.
How do I integrate this with Claude Desktop?
You can add it to your claude_desktop_config.json using the npx mcp-remote command with your specific connect token in the header.
What tools are available through the MCP interface?
The server registers 13 tools including recall, save_to_synapse, process_text, search, and neural_handover.