Overview

mcp-server-qdrant

Description:
A semantic memory server using Qdrant vector search engine for storing and retrieving context

Category: Vector Storage & Retrieval

Overview:
This server implementation provides a semantic memory layer powered by Qdrant vector search engine. It offers two main functionalities:

• Store memories in the Qdrant database
• Retrieve memories using semantic search queries

Key features:

• Automatic collection creation
• Supports FastEmbed models for encoding
• Default model: sentence-transformers/all-MiniLM-L6-v2
• Flexible deployment: cloud or local database options
• MIT Licensed

Installation & Usage:

Using uv (recommended):

uv run mcp-server-qdrant \
--qdrant-url "http://localhost:6333" \
--qdrant-api-key "your_api_key" \
--collection-name "my_collection" \
--fastembed-model-name "sentence-transformers/all-MiniLM-L6-v2"

Via Smithery:

npx @smithery/cli install mcp-server-qdrant --client claude

Configuration:

{
  "qdrant": {
    "command": "uvx",
    "args": [
      "mcp-server-qdrant",
      "--qdrant-url", 
      "http://localhost:6333",
      "--qdrant-api-key",
      "your_api_key",
      "--collection-name",
      "your_collection_name"
    ]
  }
}

Environment Variables:

• QDRANT_URL
• QDRANT_API_KEY
• COLLECTION_NAME
• FASTEMBED_MODEL_NAME
• QDRANT_LOCAL_PATH

Note: QDRANT_URL and QDRANT_LOCAL_PATH are mutually exclusive