drio
Open app

Memory MCP Server

Source

Catalog onlyCatalog onlySTDIO

Overview

Memory MCP Server is an implementation of the Model Context Protocol (MCP) server designed to manage the memory and knowledge graph for Claude.

You can install the Memory MCP Server using the command uvx memory-mcp-server or by installing it directly from the repository. Once installed, run the server using uvx memory-mcp-server. You also need to configure environment variables like DATABASE_URL for the server to function properly.

  • Supports managing and storing memory through a knowledge graph. - Integration capabilities with Claude Desktop. - Easy installation and configuration steps. - Includes testing and development guidelines.
  1. Managing user interactions and retaining context across sessions for AI applications.
  2. Enhancing the performance of AI models by providing structured knowledge access.
  3. Facilitating memory management within desktop AI interfaces like Claude Desktop.

Add to your AI client

Use these steps to connect 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": {
    "python-memory-mcp-server-evangstav": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-python-memory-mcp-server-evangstav"
      ]
    }
  }
}

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

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

What is the Model Context Protocol (MCP)?

MCP is a protocol designed to handle user context and memory management in applications.

How do I configure the server?

Set necessary environment variables, specifically `DATABASE_URL`, to allow the server to connect to an SQLite database for storing the knowledge graph.

Is it possible to run the server locally?

Yes, after installing the necessary dependencies, you can run the server locally using Python commands.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":402,"uuid":"0cb4d727-2d81-4050-a04b-b0064fd67ee2","name":"python-memory-mcp-server","title":"Memory MCP Server","description":"","avatar_url":"https://avatars.githubusercontent.com/u/52528249?v=4","created_at":"2024-12-15T06:46:13.881Z","updated_at":"2024-12-16T06:52:36.182Z","status":"created","author_name":"evangstav","author_avatar_url":"https://avatars.githubusercontent.com/u/52528249?v=4","tags":"[]","category":"knowledge-and-memory","is_featured":false,"sort":1,"url":"https://github.com/evangstav/python-memory-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"5\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-02-12 20:51:42\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Knowledge and memory