- Home
- MCP servers
- Nexus Memory
Nexus Memory
- typescript
0
GitHub Stars
typescript
Language
4 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"syntria-ai-nexus-mcp-apps": {
"command": "npx",
"args": [
"@nexus-os/mcp-memory-app"
],
"env": {
"YOUR_API_KEY": "YOUR_API_KEY"
}
}
}
}Nexus Memory MCP Server enables you to access and control the NEXUS Memory capabilities through MCP clients, providing permanent, multi-layer memory storage and fast querying across your entire digital life. It integrates with multiple MCP clients and delivers a sovereign memory experience with clear ownership, provenance, and policy enforcement.
How to use
You interact with the Nexus Memory MCP Server through an MCP client that supports standard MCP connections. Use the following patterns to connect and operate your memory: create memory entries with associated provenance, perform fast lookups, and manage memory across multiple layers (from transient working memory to long-term semantic and provenance data). You can issue memory_write to store new items, memory_search to locate items, memory_recall to retrieve items, memory_stats to inspect usage, engram_lookup to resolve constant-time references, and neural_route to navigate between related memory nodes. The system also detects tensions automatically to surface contradictions and outdated information, helping you maintain a coherent memory state across all platforms.
How to install
Before installing, ensure you have a modern Node.js environment and a compatible MCP client. The following steps install and run the Nexus Memory MCP Server integration for your preferred client.
Additional setup notes
The Nexus Memory MCP Server supports a multi-layer memory architecture and provides tooling for interaction via MCP clients. You can connect from VS Code, Claude Desktop, and ChatGPT through MCP bridges. For first-time setup, follow the installation steps, then configure your MCP client to use the Nexus Memory MCP entry as shown in the official examples.
Available tools
memory_write
Stores new memory items with optional provenance across L1-L6 layers.
memory_search
Queries memory to locate items across layers using various criteria.
memory_recall
Retrieves specific memory items by identifier or query.
memory_stats
Provides storage usage, growth metrics, and layer health information.
engram_lookup
Performs constant-time lookups to resolve memory references using ENGRAM indexing.
neural_route
Navigates through related memory paths, suggesting efficient traversal and retrieval routes.