drio
Open app

optimized-memory-mcp-server

Source

Catalog onlyCatalog onlySTDIO

Overview

The Optimized Memory MCP Server is a project designed to test and demonstrate Claude AI's coding abilities, focusing on effective AI workflows and prompt design. It implements a persistent memory system using a local knowledge graph, allowing Claude to remember user information across chats.

To use the server, set it up with Docker or NPX, and configure it in your claude_desktop_config.json. You can then interact with the server through various API endpoints to manage entities and their relationships.

  • Persistent memory using a local knowledge graph - API for creating and managing entities and relations - Ability to add, delete, and search observations - Supports Docker and NPX for easy setup
  1. Personalizing user interactions by remembering preferences and behaviors.
  2. Managing relationships and observations for enhanced AI conversations.
  3. Building a knowledge base for applications requiring user context.

Add to your AI client

Use these steps to connect optimized-memory-mcp-server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

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

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

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

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

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

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "optimized-memory-mcp-server-agentwong": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-optimized-memory-mcp-server-agentwong"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

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

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

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

FAQ

Can I use this server for any type of memory management?

Yes! The server is designed for flexible memory management across various applications.

Is there a limit to the number of entities I can create?

No, you can create as many entities as needed, but performance may vary based on the size of the knowledge graph.

How do I retrieve information from the memory?

You can use the `read_graph` API to retrieve the entire knowledge graph or `search_nodes` to find specific entities.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1186,"uuid":"98c18853-8cf8-4db9-863a-32768b4252f6","name":"optimized-memory-mcp-server","title":"optimized-memory-mcp-server","description":null,"avatar_url":"https://avatars.githubusercontent.com/u/43461848?v=4","created_at":"2025-01-28T02:37:05.952Z","updated_at":"2025-02-23T07:13:16.068Z","status":"created","author_name":"AgentWong","author_avatar_url":"https://avatars.githubusercontent.com/u/43461848?v=4","tags":"optimized-memory,mcp-server,knowledge-graph","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/AgentWong/optimized-memory-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data