MCP Server Qdrant

🚀 MCP Server for Qdrant

A Machine Control Protocol (MCP) server for storing and retrieving information in the Qdrant vector database.

🚀 Quick Start

The MCP Server for Qdrant is designed to store and retrieve text information in the Qdrant vector database. It supports semantic search and integrates FastEmbed for text embedding.

✨ Features

• Store text information in Qdrant with optional metadata.
• Support semantic search to find stored information.
• Integrate FastEmbed for text embedding.
• Configure via environment variables.
• Support Docker deployment.

📦 Installation

Using pip

pip install mcp-server-qdrant

From Source Code

git clone https://github.com/your-org/mcp-server-qdrant.git
cd mcp-server-qdrant
make setup

📚 Documentation

Configuration

Configure the server through environment variables. You can create a .env file based on the .env.example file:

cp .env.example .env

Edit the .env file to configure the server:

# Qdrant configuration
QDRANT_URL=http://localhost:6333
QDRANT_API_KEY=your-api-key

# Collection name
COLLECTION_NAME=memories

# Embedding provider configuration
EMBEDDING_PROVIDER=fastembed
EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

Usage

Local Run

python -m mcp_server_qdrant.main

Or use the make command:

make run

Docker

docker-compose up

Tools

The MCP server provides the following tools:

qdrant-store

Store information in the Qdrant database.

information: The text content to be stored.
metadata: Optional JSON metadata associated with the text.

qdrant-find

Find information in the Qdrant database using semantic search.

query: The search query.

Development

Testing

make test

Formatting

make format

Code Checking

make lint

Building

make build

📄 License

Apache License 2.0