jtsang4/better-qdrant-mcp

Python

8 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.

OPENAI_API_KEY secret Required: OpenAI API key for generating embeddings
OPENAPI_API_KEY secret Optional: OpenAI API key (alternative name)
QDRANT_URL Optional: Qdrant server URL (Docker Compose default: http://qdrant:6333)
QDRANT_API_KEY secret Optional: Qdrant API key (for Qdrant Cloud)
COLLECTION_NAME Optional: Default collection name
OPENAI_BASE_URL secret Optional: Custom OpenAI API base URL
OPENAI_EMBEDDING_MODEL secret Optional: OpenAI embedding model to use
MCP_PATH Optional: MCP transport configuration

Best match Fly.io Anything Dockerized — requires the Fly CLI.

macOS

brew install flyctl && fly launch --from https://github.com/jtsang4/better-qdrant-mcp

Linux

curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/jtsang4/better-qdrant-mcp

Windows (PowerShell)

iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/jtsang4/better-qdrant-mcp

Or deploy to a different host