mcp-server-qdrant

What is this MCP

This is a Model Context Protocol (MCP) server implementation for Qdrant, a vector search engine. It provides a semantic memory layer on top of Qdrant, enabling LLM applications to store and retrieve information using vector similarity search.

How to use this MCP

The server can be run via UVX, Docker, or directly installed in development environments like VS Code. It requires configuration of environment variables including QDRANT_URL and COLLECTION_NAME. The server provides two main tools: qdrant-store for storing information and qdrant-find for retrieving relevant information.

What this MCP can be used for

This MCP server enables semantic memory capabilities for LLM applications, allowing them to store and recall information contextually. Specific use cases include code snippet storage/retrieval for IDEs, enhancing chat interfaces with memory, and creating custom AI workflows that require persistent, searchable memory.