Provides containerization support for running the MCP server in isolated environments, with Docker Compose configuration included for easy deployment.
Enables configuration of the server through environment variables stored in .env files, supporting settings for connection details and model parameters.
Supports installation from source using Git for developers who want to modify or contribute to the codebase.
Hosts the source code repository, allowing installation directly from GitHub and potentially supporting issue tracking and contributions.
Provides a Makefile with commands for setup, running, testing, formatting, linting, and building the server application.
Provides Python-based installation, configuration, and execution options for deploying and running the MCP server.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server for Qdrantsearch for documents about machine learning embeddings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for Qdrant
A Machine Control Protocol (MCP) server for storing and retrieving information from a Qdrant vector database.
Features
Store text information with optional metadata in Qdrant
Semantic search for stored information
FastEmbed integration for text embeddings
Environment-based configuration
Docker support
Related MCP server: MCP-Ragdocs
Installation
Using pip
pip install mcp-server-qdrantFrom source
git clone https://github.com/your-org/mcp-server-qdrant.git
cd mcp-server-qdrant
make setupConfiguration
Configuration is done through environment variables. You can create a .env file based on the .env.example file:
cp .env.example .envEdit 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-v2Usage
Running locally
python -m mcp_server_qdrant.mainOr using the make command:
make runDocker
docker-compose upTools
The MCP server provides the following tools:
qdrant-store
Stores information in the Qdrant database.
information: The text to store
metadata: Optional JSON metadata to associate with the textqdrant-find
Searches for information in the Qdrant database using semantic search.
query: The search queryDevelopment
Testing
make testFormatting
make formatLinting
make lintBuilding
make buildLicense
Apache License 2.0