MCP Memory Server with Qdrant Persistence

Source

MCP server providing a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database

Catalog onlyCatalog onlySTDIO

Overview

MCP Memory Server is a server that provides a knowledge graph implementation with semantic search capabilities powered by the Qdrant vector database.

To use the MCP Memory Server, set up the environment variables, install dependencies, build the server, and add it to the MCP settings.

Graph-based knowledge representation with entities and relations - File-based persistence (memory.json) - Semantic search using Qdrant vector database - OpenAI embeddings for semantic similarity - HTTPS support with reverse proxy compatibility

Managing complex knowledge graphs for applications.
Performing semantic searches to find related entities and relations.
Integrating with other services that require knowledge representation.

Add to your AI client

Use these steps to connect MCP Memory Server with Qdrant Persistence 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-qdrant-memory-delorenj": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-qdrant-memory-delorenj"
      ]
    }
  }
}

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

Claude Code

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

.mcp.json (project root)

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

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

What is required to run the MCP Memory Server?

You need to set environment variables for OpenAI API key, Qdrant server URL, and Qdrant API key.

Can I use it with a reverse proxy?

Yes! The server supports HTTPS and can be configured to work with reverse proxies like Nginx or Apache.

Is there a license for this project?

Yes, the project is licensed under MIT.

Research and data