Qdrant MCP Server

What is Qdrant MCP Server?

An MCP server for interacting with the Qdrant vector database. It provides tools for managing vectors, performing similarity searches, and automatic text-to-vector embedding using FastEmbed. It is intended for developers who want to integrate vector search capabilities into an MCP-based application.

How to use Qdrant MCP Server?

Configure a .env file with Qdrant connection settings and default collection parameters. Install the package with pip install -e . and run the server with the command qdrant-mcp-server. Alternatively, build and run a Docker container using docker build -t qdrant-mcp-server . and docker run with appropriate environment variables.

Key features of Qdrant MCP Server

• Automatic text-to-vector embedding using FastEmbed
• Store and retrieve text content with vector search
• Use default collection configuration through environment variables
• Text similarity search by content
• Efficient embedding with optimized models

Use cases of Qdrant MCP Server

• Storing text documents and later performing semantic similarity searches
• Batch uploading multiple texts as embeddings for indexing
• Searching a Qdrant collection with metadata filters
• Managing individual points: get, delete, or count points in a collection

FAQ from Qdrant MCP Server

How do I configure the Qdrant connection?

Set QDRANT_HOST, QDRANT_PORT, QDRANT_API_KEY, and QDRANT_VERIFY_SSL in a .env file (see .env.example). The default host is localhost on port 6333.

Can I change the embedding model?

Yes. Set the EMBEDDING_MODEL environment variable to any model supported by FastEmbed (default is BAAI/bge-small-en-v1.5).

How do I use self-signed certificates with my Qdrant server?

Set QDRANT_VERIFY_SSL=False in the .env file or when running the Docker container to disable SSL certificate verification.

How do I run the server with Docker?

Build the image with docker build -t qdrant-mcp-server ., then run it with docker run -p 8000:8000 --env QDRANT_HOST=<your-host> --env QDRANT_PORT=<your-port> --env QDRANT_VERIFY_SSL=<True|False> qdrant-mcp-server.

How can I run the test suite?

Install development dependencies with pip install -e ".[dev]" and run cd tests && ./run_tests.py or pytest -xvs tests/.