Memory Nexus MCP Server

by kairosmobius Your server? Claim it

local only

Memory Nexus MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 41 installs a week from npm. Last commit 11 Feb 2026.

Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.

Installs per day peak 11 · avg 4 · +242% w/w

a month agotoday

Installs / week

npm · @memory-nexus/mcp

Stars

0 open issues

11 Feb 2026

Last commit

no releases in 90 days

MIT

License

JavaScript

Nothing serious here today

Today is the operative word: we check Memory Nexus MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add memory-nexus-mcp -- npx -y @memory-nexus/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memory-nexus-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@memory-nexus/mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.memory-nexus-mcp]
command = "npx"
args = ["-y", "@memory-nexus/mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "memory-nexus-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@memory-nexus/mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "memory-nexus-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@memory-nexus/mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: NEXUS_API_KEY (API key for Memory Nexus).

Alternatives to Memory Nexus MCP

same job, measured the same way

Nexus Memory MCP

by kairosmobius

Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.

45 installs/wk local only

Graph-Mem

by sathvik-1007

Persistent knowledge-graph memory for AI agents, with local semantic search. No API keys.

92 installs/wk local only

Komplyt Zero

by komplyzen

Persistent working memory for AI agents: a knowledge graph with semantic search and decay.

154 installs/wk answering

Codeseeker

by jghiringhelli

Graph-powered code intelligence with semantic search and knowledge graph for AI assistants

391 installs/wk local only

Memory

by humaux

Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.

answering

Octobrain

by muvon

Persistent memory for AI assistants with semantic search and knowledge graph relationships.

844 installs/wk local only

Ori Memory

by aayoawoyemi

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.

143 installs/wk local only

Alaya MCP

by securityronin

Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall

132 installs/wk local only

Memory Nexus MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Memory Nexus MCP?

Memory Nexus MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @memory-nexus/mcp was installed 41 times last week.

How do I connect Memory Nexus MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @memory-nexus/mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Memory Nexus MCP?

The npm package @memory-nexus/mcp was installed 41 times in the last week. Week over week that is +242%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Memory Nexus MCP open source?

Yes — it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.