About MCP Server for Qdrant
MCP Server for Qdrant connects MCP clients to a Qdrant vector database for storing text and retrieving it with semantic search. It is suited to applications that need searchable text records with optional metadata.
Key features
- 01Store text with optional metadata
- 02Semantic search in Qdrant
- 03FastEmbed text embeddings
- 04Environment-based configuration
- 05Docker support
Use cases
- 01Save information for later retrieval
- 02Find stored text by meaning
MCP support
Exposes qdrant-store and qdrant-find tools to MCP clients for writing information to Qdrant and searching it semantically.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP 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
Installation
Using pip
pip install mcp-server-qdrant
From source
git clone https://github.com/your-org/mcp-server-qdrant.git
cd mcp-server-qdrant
make setup
Configuration
Configuration is done 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
Running locally
python -m mcp_server_qdrant.main
Or using the make command:
make run
Docker
docker-compose up
Tools
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 text
qdrant-find
Searches for information in the Qdrant database using semantic search.
query: The search query
Development
Testing
make test
Formatting
make format
Linting
make lint
Building
make build
License
Apache License 2.0
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.