This repository provides an example of a Model Context Protocol (MCP) server for Qdrant, a vector search engine, enabling seamless integration between LLM applications and the Qdrant database as a
This repository provides an example of a Model Context Protocol (MCP) server for Qdrant, a vector search engine, facilitating seamless integration between LLM applications and external data sources. It acts as a semantic memory layer on top of Qdrant, enabling storage and retrieval of information.
The server includes two main tools: qdrant-store
for storing information with optional metadata in Qdrant, and qdrant-find
for retrieving relevant information based on a query. Configuration is managed through environment variables such as QDRANT_URL
, QDRANT_API_KEY
, and COLLECTION_NAME
.
Installation options include using uvx
, Docker, or Smithery. The server supports stdio
and sse
transport protocols. It can be integrated with tools like Claude Desktop and Cursor/Windsurf, enhancing them with code search capabilities by customizing tool descriptions. For example, it can store code snippets with descriptions and retrieve them based on semantic search queries. The MCP inspector can be used for local testing. Licensed under Apache 2.0.
qdrant/mcp-server-qdrant
December 2, 2024
March 28, 2025
Python