Qdrant OpenAI

Provides semantic search over Qdrant collections using OpenAI embeddings with list and info capabilities.

python

6

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "amansingh0311-mcp-qdrant-openai": {
      "command": "python",
      "args": [
        "mcp_qdrant_server.py"
      ],
      "env": {
        "QDRANT_URL": "http://localhost:6333",
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "QDRANT_API_KEY": "YOUR_QDRANT_API_KEY"
      }
    }
  }
}

This MCP server enables vector search and semantic querying by connecting a Qdrant vector database with OpenAI embeddings. You can search, list, and inspect Qdrant collections directly through MCP-powered tooling, making it easy to build intelligent search experiences on top of your data.

How to use

You will run the server locally or via the MCP CLI and then interact with it using MCP clients. The server exposes tools to query a Qdrant collection with semantic embeddings, list available collections, and fetch collection details.

To use the server from an MCP client, first start the server using one of the provided startup commands. Then issue tool calls from your MCP client to perform semantic searches, list collections, or view collection information.

How to install

Prerequisites you need before installation are Python 3.10 or newer, a Qdrant instance (local or remote), and an OpenAI API key.

Step 1: Install dependencies for the server. You need Python and the required Python packages.

pip install -r requirements.txt

Configure and run the server

Set your environment variables to enable OpenAI embeddings and connect to Qdrant. These values are used by the server at runtime.

Required environment variables:

OPENAI_API_KEY: Your OpenAI API key QDRANT_URL: URL to your Qdrant instance (default: http://localhost:6333) QDRANT_API_KEY: Your Qdrant API key (if applicable)

Run the server directly

python mcp_qdrant_server.py

Run with MCP CLI

mcp dev mcp_qdrant_server.py

Installing in Claude Desktop

mcp install mcp_qdrant_server.py --name "Qdrant-OpenAI"

Available tools and what they do

query_collection — Search a Qdrant collection using semantic search with OpenAI embeddings.

list_collections — List all available collections in the Qdrant database.

collection_info — Get information about a specific collection.

Notes on configuration and usage

The server relies on a Qdrant instance and OpenAI embeddings to perform vector search. The default Qdrant URL is http://localhost:6333, but you can point to a remote instance by setting QDRANT_URL. Ensure your OpenAI API key is active and you have any necessary Qdrant API access configured.

Troubleshooting and tips

If you encounter connectivity issues, verify that the Qdrant service is reachable at the URL you provided and that the API key for OpenAI is valid. Check that Python 3.10+ is in use and that the required Python packages installed without errors.

Available tools

query_collection

Search a Qdrant collection using semantic search with OpenAI embeddings.

list_collections

List all available collections in the Qdrant database.

collection_info

Get information about a specific collection.