Memory Custom

simple memory mcp server with custom memory location

Catalog onlyCatalog onlySTDIO

Overview

Memory Custom is a project that enhances the Memory server by allowing users to create and manage a knowledge graph that captures interactions via a language model (LLM).

To use Memory Custom, clone the repository, install the dependencies, configure the memory file path, and run the server locally to start managing your knowledge graph.

Custom memory paths for project-specific storage. - Timestamping for tracking memory creation and modifications. - API endpoints for various memory management tasks.

Organizing memory data for different projects.
Tracking interactions and changes over time.
Enhancing user engagement through personalized memory updates.

Add to your AI client

Use these steps to connect Memory Custom 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-custom-bro3886": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

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-custom-bro3886": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-memory-custom-bro3886": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

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-custom-bro3886": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-memory-custom-bro3886": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

Cline

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

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-memory-custom-bro3886": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-memory-custom-bro3886"
      ]
    }
  }
}

FAQ

What is the purpose of custom memory paths?

Custom memory paths allow for better organization of memory data specific to each project.

How do I run the server?

You can run the server by building the project and executing the command `node dist/index.js`.

Is there an API available?

Yes, the server exposes several API endpoints for memory management tasks.

Research and data