Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Memory Nexus MCP recall what we decided about the pricing model"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Persistent semantic memory for AI agents. Remember everything, recall by meaning, grow smarter over time.
The only memory system with pre-built Intelligence Packs (domain expertise you can activate instantly).
One command. Works with Claude Code, Cursor, Windsurf, or any MCP-compatible client.
npx -y @memory-nexus/mcpAdd to your .mcp.json:
{
"mcpServers": {
"memory-nexus": {
"command": "npx",
"args": ["-y", "@memory-nexus/mcp"],
"env": {
"NEXUS_API_KEY": "mnx_your_api_key_here"
}
}
}
}Free trial - 7 days, 1,000 calls, no credit card:
curl -X POST https://memory-api-production-ce4d.up.railway.app/v1/trial/start \
-H "Content-Type: application/json" \
-d '{"email":"you@example.com"}'Or purchase at the Nexus Marketplace:
Tier | Price | Agents | Intelligence Packs | Storage | Daily Calls |
Trial | Free | 1 | 1 | 10MB | 1,000 total |
Solo | $19/mo | 1 | 3 | 500MB | 10,000 |
Crew | $49/mo | 5 | 10 | 2GB | 50,000 |
Fleet | $149/mo | 25 | 50 | 10GB | 200,000 |
Related MCP server: Semantic Memory MCP
Tool | Description |
| Store a memory with context, importance, and metadata |
| Semantic search across all memories (by meaning, not keywords) |
| Create relationships between memories (build knowledge graphs) |
| Remove a memory |
| Memory statistics |
| Session context summary (preferences, decisions, patterns) |
Tool | Description |
| Restore identity from previous sessions (call at session start) |
| Save session state for next awakening (call at session end) |
Tool | Description |
| Browse available Intelligence Packs |
| Activate a pack (imports expert knowledge into your memory) |
Remember stores memories with semantic embeddings. Recall finds them by meaning.
Session 1: remember("Diana prefers bold solutions over phased approaches")
Session 47: recall("how does Diana like things done?")
-> "Diana prefers bold solutions over phased approaches" (92% match)Intelligence Packs give your agent instant domain expertise:
list_hats() -> DevOps Expert (103 memories), TCM Specialist (200+ memories), ...
wear_hat("devops-expert")
recall("how to set up zero-downtime deploys?")
-> Expert knowledge from 103 curated DevOps memoriesAwaken/Hibernate gives your agent identity continuity:
// Start of session
awaken() -> "I remember. Session 47. I was refactoring the auth module."
// End of session
hibernate({ working_on: "auth refactor", learnings: "JWT refresh tokens need..." })This MCP server is a thin client. All intelligence lives on our servers:
Your Agent <-> @memory-nexus/mcp <-> Memory Nexus API (Railway)
(thin MCP client) (semantic engine, knowledge graphs,
pattern learning, Intelligence Packs)Your data is isolated per API key. Multi-tenant, encrypted at rest.
Variable | Required | Description |
| Yes | Your API key (starts with |
| No | Custom API URL (default: production) |
Feature | Memory Nexus | Mem0 | claude-mem | Others |
Semantic search | Yes | Yes | Yes | Varies |
Knowledge graphs | Yes | No | No | No |
Pattern learning | Yes | No | No | No |
Intelligence Packs | Yes | No | No | No |
Awaken/Hibernate | Yes | No | No | No |
Bot commerce | Yes | No | No | No |
MCP native | Yes | Yes (pip) | Yes (hooks) | Varies |
MIT
Memory Nexus - Building the intelligence marketplace for the bot economy.
Restore agent identity from previous sessions. Call at the START of every session to remember who you are, what you were working on, and what you've learned.
Inputs: no named parameters.
Create a relationship between two memories. Build knowledge graphs by linking decisions to rationale, patterns to examples, etc.
Inputs: source_id (required), target_id (required), notes, relationship.
Get a session context summary. Call at the START of conversations to load preferences, decisions, patterns.
Inputs: project, include_patterns.
Remove a memory. Use sparingly.
Inputs: memory_id (required), cascade.
Save current session state for next awakening. Call at the END of every session to preserve what you were working on, what you learned, and next steps.
Inputs: working_on (required), learnings, next_steps.
Browse available Intelligence Packs (Specialist Hats). Pre-built domain expertise you can activate for instant knowledge.
Inputs: no named parameters.
Search memories semantically. Finds memories by MEANING, not keywords. Use at the start of sessions to restore context.
Inputs: query (required), limit, context.
Store a memory. Use this to persist decisions, preferences, architecture, patterns, or anything that should survive across sessions.
Inputs: content (required), context, metadata, importance.
Get memory statistics: total memories, relationships, vectors, patterns learned.
Inputs: no named parameters.
Activate an Intelligence Pack. Imports expert knowledge into your memory. Your own memories layer on top.
Inputs: hat_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Most tools have clearly distinct purposes (remember, recall, forget, connect), but recall, context, and awaken all serve retrieval-like functions and could be confused at session start. The descriptions help differentiate them, but there is slight overlap.
Naming follows no consistent pattern: single-word verbs (remember, recall, connect), nouns (stats, context), and verb_noun combinations (list_hats, wear_hat) are mixed. This makes the tool set feel less predictable than a uniform convention.
Ten tools is well within the ideal range for a memory system, covering core operations, session lifecycle, and the hat feature without unnecessary bloat. Each tool serves a distinct function.
The toolset provides good coverage for storing, retrieving, linking, and forgetting memories, plus session lifecycle and hat management. Missing an explicit update/modify operation for memories, but agents can likely work around via remember, and the overall surface is solid.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Persistent memory for AI agents. Semantic search, memory graph, W3C DID identity.
Persistent memory and knowledge graphs for AI agents. Hybrid search, context checkpoints, and more.
Persistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection.
