qdrant_mcp-server-qdrant

The mcp-server-qdrant is a Model Context Protocol server designed to interface with the Qdrant vector search engine, providing a semantic memory layer for storing and retrieving memories. It allows for the integration of LLM applications with the Qdrant database, enabling efficient memory management and retrieval. The server supports the use of FastEmbed models for encoding memories and can be configured to run in both local and server modes. It is designed to be easily installed and configured, with support for environment variables and integration with platforms like Claude Desktop.

Features

• Semantic memory layer on top of Qdrant database
• Supports FastEmbed models for memory encoding
• Configurable via environment variables
• Integration with Claude Desktop
• Local and server mode support

MCP Tools

• qdrant-store-memory: Store a memory in the Qdrant database
• qdrant-find-memories: Retrieve a memory from the Qdrant database

Usage with Different Platforms

Claude Desktop

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

Local Qdrant

{
  "qdrant": {
    "command": "uvx",
    "args": [
      "mcp-server-qdrant", 
      "--qdrant-local-path",
      "/path/to/qdrant/database",
      "--collection-name",
      "your_collection_name"
    ]
  }
}