drio
Open app

Knowledge Graph Memory Server

Source

MCP server for enabling memory for Claude through a knowledge graph

Catalog onlyCatalog onlySTDIO

Overview

MCP Memory Py is a knowledge graph memory server designed to enable persistent memory for AI models like Claude, allowing them to remember user information across chats.

To use MCP Memory Py, set up the server with the provided configuration in your Claude Desktop environment, and interact with it through the defined API endpoints to manage entities, relations, and observations.

  • Persistent memory storage using a local knowledge graph - API for creating and managing entities and relations - Ability to add, delete, and search observations - Integration with Claude for personalized interactions
  1. Enhancing AI chatbots with memory capabilities
  2. Storing user preferences and behaviors for personalized experiences
  3. Managing complex relationships and interactions in AI applications

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

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

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

Can MCP Memory Py be used with other AI models?

While designed for Claude, it can potentially be adapted for other models with similar memory requirements.

Is there a limit to the number of entities or observations?

The limit depends on the storage capacity of the server and the design of the knowledge graph.

How can I test the server?

You can run unit tests using the command `uv run pytest` to ensure functionality.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1424,"uuid":"cf895a49-1e66-499e-9534-5c44dbbf4e11","name":"mcp-memory-py","title":"Knowledge Graph Memory Server","description":"MCP server for enabling memory for Claude through a knowledge graph","avatar_url":"https://avatars.githubusercontent.com/u/1084583?v=4","created_at":"2025-02-20T15:44:28.232Z","updated_at":"2025-02-23T07:20:28.655Z","status":"created","author_name":"edobez","author_avatar_url":"https://avatars.githubusercontent.com/u/1084583?v=4","tags":"knowledge-graph,memory-server,AI-assistant","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/edobez/mcp-memory-py","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