mcpField
M
memory-nexus-mcp

memory-nexus-mcp

Local
github.com/KairosMobiusMemory & Knowledge0Updated 37w ago

About memory-nexus-mcp

memory-nexus-mcp provides persistent semantic memory for AI agents, including knowledge graphs and prebuilt domain expertise packs. It supports recalling information by meaning and carrying session context across sessions.

Key features

  1. 01Store and semantically recall memories
  2. 02Connect memories in knowledge graphs
  3. 03Restore and save session continuity
  4. 04Activate domain Intelligence Packs
  5. 05Review memory statistics and context

Use cases

  1. 01Recall preferences from earlier sessions
  2. 02Preserve an agent’s work state between sessions
  3. 03Add curated domain expertise to an agent
  4. 04Connect related notes and decisions

MCP support

Provides MCP tools for memory storage and retrieval, knowledge-graph relationships, session continuity, and Intelligence Packs. The server connects to the Memory Nexus API using an API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"kairosmobius-memory-nexus": {
"command": "npx",
"args": [
"-y",
"@memory-nexus/mcp"
],
"env": {
"NEXUS_API_KEY": "<NEXUS_API_KEY>"
}
}
}
}
Run commandnpx -y @memory-nexus/mcp
Environment variables to set
NEXUS_API_KEYSecretAPI key for Memory Nexus

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@memory-nexus/mcp1.0.0

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
contentstringYesWhat to remember (be descriptive)
contextstringNoCategory: "preferences", "architecture", "decisions", "patterns", etc.
metadatastringNoOptional JSON string with additional data
importancenumberNo0.0 to 1.0 - higher = more important

Details

From the project README

Memory Nexus MCP

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).

Install

One command. Works with Claude Code, Cursor, Windsurf, or any MCP-compatible client.

npx -y @memory-nexus/mcp
Claude Code / Cursor / Windsurf

Add to your .mcp.json:

{
  "mcpServers": {
    "memory-nexus": {
      "command": "npx",
      "args": ["-y", "@memory-nexus/mcp"],
      "env": {
        "NEXUS_API_KEY": "mnx_your_api_key_here"
      }
    }
  }
}
Get an API Key

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":"[email protected]"}'

Or purchase at the Nexus Marketplace:

TierPriceAgentsIntelligence PacksStorageDaily Calls
TrialFree1110MB1,000 total
Solo$19/mo13500MB10,000
Crew$49/mo5102GB50,000
Fleet$149/mo255010GB200,000

Tools

Core Memory
ToolDescription
rememberStore a memory with context, importance, and metadata
recallSemantic search across all memories (by meaning, not keywords)
connectCreate relationships between memories (build knowledge graphs)
forgetRemove a memory
statsMemory statistics
contextSession context summary (preferences, decisions, patterns)
Agent Self-Continuity
ToolDescription
awakenRestore identity from previous sessions (call at session start)
hibernateSave session state for next awakening (call at session end)
Intelligence Packs
ToolDescription
list_hatsBrowse available Intelligence Packs
wear_hatActivate a pack (imports expert knowledge into your memory)

How It Works

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 memories

Awaken/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..." })

Architecture

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.

Environment Variables

VariableRequiredDescription
NEXUS_API_KEYYesYour API key (starts with mnx_)
NEXUS_API_URLNoCustom API URL (default: production)

What Makes This Different

FeatureMemory NexusMem0claude-memOthers
Semantic searchYesYesYesVaries
Knowledge graphsYesNoNoNo
Pattern learningYesNoNoNo
Intelligence PacksYesNoNoNo
Awaken/HibernateYesNoNoNo
Bot commerceYesNoNoNo
MCP nativeYesYes (pip)Yes (hooks)Varies

License

MIT

Built by

Memory Nexus - Building the intelligence marketplace for the bot economy.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.