Skip to content

Memory MCP Server

Knowledge graph-based persistent memory system. Store and retrieve contextual information across conversations.

Capabilities
Knowledge Graph Persistence Context Entities
Maintained by
MCP project (reference server)
Hosting
Runs locally on your machine
Authentication
None beyond local access
Last checked

How to connect the Memory MCP server

Pick your AI client and paste the snippet. New to this? Our guide to how MCP clients and servers fit together explains what each piece does.

Claude Code

Terminal
claude mcp add --transport stdio memory \
  -- npx -y @modelcontextprotocol/server-memory
Full Claude Code setup guide →

Claude Desktop

claude_desktop_config.json (Settings → Developer → Edit Config)
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}

Fully quit and reopen Claude Desktop after saving.

Full Claude Desktop setup guide →

Cursor

~/.cursor/mcp.json (or .cursor/mcp.json in a project)
{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}
Full Cursor setup guide →

VS Code

.vscode/mcp.json
{
  "servers": {
    "memory": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ]
    }
  }
}
Full VS Code setup guide →

Frequently asked questions

What is the Memory MCP server?

It is a Model Context Protocol (MCP) server — a small piece of software that gives AI assistants like Claude a secure, governed connection to Memory. Knowledge graph-based persistent memory system. Store and retrieve contextual information across conversations.

Is there an official Memory MCP server?

Yes. The Memory MCP server is an official integration, maintained by the vendor or the Model Context Protocol project, which makes it the safest default for business use. It is maintained by MCP project (reference server).

Is the Memory MCP server hosted, or do I run it myself?

It runs locally. Your AI client starts it on your own machine with npx, and it talks to the client over standard input and output rather than the network.

Do I need an API key for the Memory MCP server?

No. It runs on your machine with your own permissions, so there is no key to create.

What can an AI assistant actually do with Memory?

Through this server an assistant can work with knowledge graph, persistence, context, entities — reading from and acting on Memory directly instead of you copy-pasting between windows. What you allow it to do is controlled by the permissions you grant.

How do I set this up for my business?

The setup section above has copy-paste config for Claude Code, Claude Desktop, Cursor and VS Code. If you want it rolled out across a team with permissions, governance and support handled, that is what Crox's Build engagement covers.

New to MCP? Start with our plain-English guide to the Model Context Protocol or see how to connect AI to your business tools without writing code .

Done-for-you integration

Want this connected to your business — with governance handled?

Crox maps your processes, connects AI to the tools you already use, and keeps it working as models change. Start with a readiness assessment or talk to us about a build.