Qdrant MCP Server vs Memory (Knowledge Graph)

A side-by-side comparison of two AI, Data & Knowledge servers — tools, transport, auth, maintenance, and copy-paste config for each.

	Qdrant MCP Server Official Qdrant server using a vector collection as semantic memory: store and find embeddings. Verified stdio (local) API key Python	Memory (Knowledge Graph) Official MCP server providing persistent, file-backed knowledge-graph memory across sessions. Verified stdio (local) No auth TypeScript
Category	AI, Data & Knowledge	AI, Data & Knowledge
Language	Python	TypeScript
Transport	stdio (local)	stdio (local)
Auth	API key	None
GitHub stars	1.1k	74k
Last commit	1 month ago	5 months ago
Verified
Actively maintained
Install	`uvx mcp-server-qdrant`	`npx -y @modelcontextprotocol/server-memory`
Repo	Open	Open

Verdict

Pick Qdrant MCP Server if you prefer its approach (official qdrant server using a vector collection as semantic memory: store and find embeddings).

Pick Memory (Knowledge Graph) if you prefer the more popular, battle-tested option, and you want zero-setup with no API key.

Add Qdrant MCP Server

Install / run

uvx mcp-server-qdrant

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "qdrant-mcp-server": {
      "command": "uvx",
      "args": [
        "mcp-server-qdrant"
      ],
      "env": {
        "QDRANT_URL": "https://<your-cluster>.cloud.qdrant.io:6333",
        "QDRANT_API_KEY": "<your-api-key>",
        "COLLECTION_NAME": "<your-collection-name>",
        "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
      }
    }
  }
}

Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.

Add Memory (Knowledge Graph)

Install / run

npx -y @modelcontextprotocol/server-memory

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memory-knowledge-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-memory"
      ],
      "env": {
        "MEMORY_FILE_PATH": "/absolute/path/to/memory.jsonl"
      }
    }
  }
}

FAQ

Qdrant MCP Server or Memory (Knowledge Graph) — which is better?

Pick Qdrant MCP Server if you prefer its approach (official qdrant server using a vector collection as semantic memory: store and find embeddings). Pick Memory (Knowledge Graph) if you prefer the more popular, battle-tested option, and you want zero-setup with no API key.

Can I use both Qdrant MCP Server and Memory (Knowledge Graph)?

Yes — MCP clients let you enable multiple servers at once. Add both configs to your client's mcpServers and use whichever tool fits the task.

Do Qdrant MCP Server and Memory (Knowledge Graph) work with Claude, Cursor and Windsurf?

Both do. Copy the per-client config below into Claude Desktop, Cursor, or Windsurf.

View Qdrant MCP Server →View Memory (Knowledge Graph) →More comparisons →