mcp-server-qdrant

Overview

This is an official MCP server implementation for Qdrant, a vector search engine. It provides tools to store and retrieve semantic memories, acting as a memory layer for AI applications. The server supports both remote and local Qdrant instances, with flexible configuration options including embedding models and search limits.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• qdrant-storeinformation: string, metadata?: JSON, collection_name?: string

  Store information in the Qdrant database with optional metadata

  Try:Store information about React hooksTry:Save this code snippet with metadataTry:Store document about machine learning best practices
• qdrant-findquery: string, collection_name?: string

  Retrieve relevant information from the Qdrant database

  Try:Find information about React hooksTry:Search for code snippets related to authenticationTry:Look up documents about machine learning best practices

Comparable tools

Installation

QDRANT_URL="http://localhost:6333" \
COLLECTION_NAME="my-collection" \
EMBEDDING_MODEL="sentence-transformers/all-MiniLM-L6-v2" \
uvx mcp-server-qdrant

docker build -t mcp-server-qdrant .
docker run -p 8000:8000 \
  -e FASTMCP_SERVER_HOST="0.0.0.0" \
  -e QDRANT_URL="http://your-qdrant-server:6333" \
  -e QDRANT_API_KEY="your-api-key" \
  -e COLLECTION_NAME="your-collection" \
  mcp-server-qdrant

{
  "qdrant": {
    "command": "uvx",
    "args": ["mcp-server-qdrant"],
    "env": {
      "QDRANT_URL": "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333",
      "QDRANT_API_KEY": "your_api_key",
      "COLLECTION_NAME": "your-collection-name",
      "EMBEDDING_MODEL": "sentence-transformers/all-MiniLM-L6-v2"
    }
  }
}

FAQ

What embedding models are supported?

Currently only FastEmbed models are supported, with 'sentence-transformers/all-MiniLM-L6-v2' as the default.

Can I use this with local Qdrant?

Yes, you can use QDRANT_LOCAL_PATH environment variable instead of QDRANT_URL to specify a local database path.

Compare mcp-server-qdrant with