mcp-server-qdrant
by qdrant
This repository provides an example of how to create a Model Context Protocol (MCP) server for Qdrant, a vector search engine. It acts as a semantic memory layer on top of the Qdrant database, enabling seamless integration between LLM applications and Qdrant for storing and retrieving memories.
Last updated: N/A
What is mcp-server-qdrant?
An official Model Context Protocol server for keeping and retrieving memories in the Qdrant vector search engine. It provides a semantic memory layer on top of Qdrant, allowing LLMs to access and store contextual information.
How to use mcp-server-qdrant?
The server is configured using environment variables such as QDRANT_URL, QDRANT_API_KEY, and COLLECTION_NAME. It can be installed using uvx, Docker, or Smithery. Once installed, it can be integrated with MCP-compatible clients like Cursor, VS Code, and Claude Code by configuring the appropriate settings and providing the necessary environment variables.
Key features of mcp-server-qdrant
Stores information in Qdrant using the
qdrant-storetool.Retrieves relevant information from Qdrant using the
qdrant-findtool.Supports various transport protocols like stdio and SSE.
Configurable embedding model (currently only fastembed is supported).
Integration with popular IDEs and tools like VS Code, Cursor, and Claude Code.
Use cases of mcp-server-qdrant
Providing context to LLMs for AI-powered IDEs.
Enhancing chat interfaces with semantic memory.
Creating custom AI workflows with external data sources.
Code search and retrieval in development environments.
FAQ from mcp-server-qdrant
What is the Model Context Protocol (MCP)?
What is the Model Context Protocol (MCP)?
MCP is an open protocol that enables seamless integration between LLM applications and external data sources and tools.
What is Qdrant?
What is Qdrant?
Qdrant is a vector search engine that is used to store and retrieve information based on semantic similarity.
How do I configure the server?
How do I configure the server?
The server is configured using environment variables. See the README for a list of available variables.
What embedding providers are supported?
What embedding providers are supported?
Currently, only the 'fastembed' embedding provider is supported.
Can I use command-line arguments to configure the server?
Can I use command-line arguments to configure the server?
No, command-line arguments are not supported anymore. Please use environment variables for all configuration.