drio
Open app

memory-mcp-server

Source

A long-term memory storage system for LLMs using the Model Context Protocol (MCP) standard. This system helps LLMs remember the context of work done over the entire history of a project, even across multiple sessions. It uses semantic search with embeddings to provide relevant context from past interactions and development decisions.

Catalog onlyCatalog onlySTDIO

Overview

Memory-mcp-server is a long-term memory storage system designed for Large Language Models (LLMs) that utilizes the Model Context Protocol (MCP) standard. It enables LLMs to retain the context of work done throughout the entire history of a project, even across multiple sessions.

To use memory-mcp-server, integrate it with your LLM application by following the setup instructions provided in the GitHub repository. Once integrated, the system will automatically manage context retention and retrieval based on past interactions.

  • Long-term memory storage for LLMs - Context retention across multiple sessions - Semantic search capabilities using embeddings for relevant context retrieval
  1. Enhancing LLMs with the ability to remember user preferences over time.
  2. Supporting complex projects where context from previous sessions is crucial for continuity.
  3. Improving user interactions by providing relevant historical context during conversations.

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

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

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

How does memory-mcp-server ensure data privacy?

Memory-mcp-server is designed with privacy in mind, ensuring that all stored data is handled securely and in compliance with data protection standards.

Can memory-mcp-server be used with any LLM?

Yes! Memory-mcp-server is compatible with various LLMs that support the Model Context Protocol (MCP).

Is there a limit to the amount of context that can be stored?

The storage capacity depends on the implementation and resources allocated to the memory-mcp-server.

Research and data