mcp-qdrant-memory
11
The MCP Memory Server with Qdrant Persistence is a server implementation that offers a knowledge graph with semantic search capabilities using Qdrant. It supports HTTPS, reverse proxies, and offers Docker support for deployment. The server handles graph-based knowledge management and semantic similarity searches using OpenAI embeddings.
MCP Memory Server with Qdrant Persistence
This MCP server provides a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database.
Features
- Graph-based knowledge representation with entities and relations
- File-based persistence (memory.json)
- Semantic search using Qdrant vector database
- OpenAI embeddings for semantic similarity
- HTTPS support with reverse proxy compatibility
- Docker support for easy deployment
Tools
Entity Management
- Create, delete entities and relations
- Add observations to entities
- Read the full knowledge graph
Semantic Search
- Search for semantically similar entities and relations
Implementation Details
- Two forms of persistence: File-based and Qdrant Vector DB
- Synchronization between file storage and Qdrant
- Semantic search process using embeddings
HTTPS and Reverse Proxy Configuration
- Support for connecting to Qdrant through HTTPS and reverse proxies
Contributing
- Fork the repository, create a branch, submit a pull request
License
MIT