drio
Open app

Knowledge Graph Memory Server

Source

Catalog onlyCatalog onlySTDIO

Overview

The Knowledge Graph Memory Server is a basic implementation of persistent memory using a local knowledge graph, allowing Claude to remember information about users across chats.

To use the server, set it up with Docker or NPX, configure it in your Claude Desktop settings, and utilize the provided API to create entities, relations, and observations.

  • Create and manage entities and their relationships in a knowledge graph. - Add, delete, and search observations related to entities. - Retrieve the entire knowledge graph structure.
  1. Personalizing user interactions by remembering user preferences.
  2. Managing complex relationships between different entities.
  3. Enhancing AI conversations with contextual memory.

Add to your AI client

Use these steps to connect Knowledge Graph Memory 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": {
    "azure-deploy-mcp-server-qianwens": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

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": {
    "azure-deploy-mcp-server-qianwens": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

{
  "mcpServers": {
    "azure-deploy-mcp-server-qianwens": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

VS Code (Copilot)

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

.vscode/mcp.json

{
  "servers": {
    "azure-deploy-mcp-server-qianwens": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "azure-deploy-mcp-server-qianwens": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

Cline

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

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "azure-deploy-mcp-server-qianwens": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-azure-deploy-mcp-server-qianwens"
      ]
    }
  }
}

FAQ

Can the server handle multiple users?

Yes! The server can manage multiple entities and their relationships simultaneously.

Is there a limit to the number of observations?

No, you can add as many observations as needed for each entity.

How is data stored?

Data is stored in a JSON format, allowing for easy retrieval and management.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":3581,"uuid":"70804eac-c885-441a-8287-df5e1abdf69d","name":"azure-deploy-mcp-server","title":"Knowledge Graph Memory Server","description":"","avatar_url":"https://avatars.githubusercontent.com/u/37290631?v=4","created_at":"$D2025-03-20T10:38:58.111Z","updated_at":"$D2025-03-20T11:11:08.143Z","status":"created","author_name":"qianwens","author_avatar_url":"https://avatars.githubusercontent.com/u/37290631?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/qianwens/azure-deploy-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"0\",\"license\":\"\",\"language\":\"TypeScript\",\"is_official\":false,\"latest_commit_time\":\"2025-03-25 17:36:22\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data