Memory MCP

Name: Memory MCP
Author: Anthropic

Persistent knowledge graph memory across AI sessions

Official

Featured

AI & ML

Install Command

npx -y @modelcontextprotocol/server-memory

Claude Desktop Config

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

Memory MCP is an officially maintained MCP server in the AI & ML category, developed by Anthropic. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.

About Memory MCP

Official Memory MCP server gives AI assistants persistent memory using a local knowledge graph.

Features

Create and store entities (people, projects, concepts)
Build relationships between entities
Recall context from previous sessions
Semantic search across stored knowledge
Update and delete stored memories

Use Cases

Remember user preferences
Track project context across sessions

Who Should Use Memory MCP?

1Chain AI models and pipelines through a unified MCP interface
2Let Claude orchestrate other AI tools and models
3Integrate embeddings, image generation, or speech APIs into your workflow
4Build multi-model workflows without writing custom integration code

How to Install Memory MCP

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.

How Memory MCP Compares

✦It is an officially maintained server — unlike community alternatives, it is built and supported by the original project team, ensuring compatibility with upstream changes.

✦It runs entirely on your local machine, so no data leaves your environment — important for teams with privacy or compliance requirements.

✦It is distributed as an npm package, making version management and updates straightforward with a single `npm update` command.