About
An official Model Context Protocol server for keeping and retrieving memories in the Qdrant vector search engine. It acts as a semantic memory layer on top of the Qdrant database, enabling semantic search and storage of information with embeddings.
Features
- Store information with optional metadata in Qdrant collections
- Retrieve relevant information using semantic search
- Support for both cloud-hosted and local Qdrant instances
- Configurable embedding models via FastEmbed
- Read-only mode support
- Multiple transport protocols (stdio, SSE, streamable-http)
Tools
qdrant-store
Store information in the Qdrant database with optional metadata. The information is automatically embedded and indexed for semantic search.
qdrant-find
Retrieve relevant information from the Qdrant database using semantic search. Returns the most relevant results based on the query.
Use Cases
- Semantic Memory Layer: Store and retrieve contextual information for LLM applications
- Code Search: Store code snippets with descriptions and search using natural language (especially useful with Cursor/Windsurf)
- Knowledge Base: Build a semantic knowledge base for AI assistants
- Document Retrieval: Store and search through documents semantically
Configuration Options
You can customize the tool descriptions using TOOL_STORE_DESCRIPTION and TOOL_FIND_DESCRIPTION to adapt the server for specific use cases like code search or documentation retrieval.
This server runs through your single 1Server connection. No extra config required.