Qdrant with OpenAI Embeddings MCP server

This server provides vector search capabilities through a combination of Qdrant vector database and OpenAI embeddings, allowing you to perform semantic searches on your data collections. The MCP (Model Context Protocol) implementation makes it easy to integrate with AI assistants like Claude.

Installation Options

Automated Installation via Smithery

To install the server automatically with Smithery:

npx -y @smithery/cli install @amansingh0311/mcp-qdrant-openai --client claude

Manual Installation

1. Clone the repository:

git clone https://github.com/yourusername/mcp-qdrant-openai.git
cd mcp-qdrant-openai

2. Install dependencies:

pip install -r requirements.txt

Configuration Requirements

Set up these environment variables before running the server:

• 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)

Running the Server

Direct Execution

python mcp_qdrant_server.py

Run with MCP CLI

mcp dev mcp_qdrant_server.py

Install in Claude Desktop

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

Available Tools

Query Collection

The query_collection tool performs semantic searches using OpenAI embeddings:

• Parameters:
  • collection_name: Name of the Qdrant collection to search
  • query_text: Natural language search query
  • limit: Maximum number of results (default: 5)
  • model: OpenAI embedding model (default: text-embedding-3-small)

List Collections

The list_collections tool shows all available collections in your Qdrant database.

Collection Info

The collection_info tool provides details about a specific collection:

• Parameters:
  • collection_name: Name of the collection to examine

Using with Claude Desktop

After installation, you can interact with your Qdrant database by asking Claude:

• "What collections are available in my Qdrant database?"
• "Search for documents about climate change in my 'documents' collection."
• "Show me information about the 'articles' collection."

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "qdrant-openai" '{"command":"python","args":["mcp_qdrant_server.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "qdrant-openai": {
            "command": "python",
            "args": [
                "mcp_qdrant_server.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "qdrant-openai": {
            "command": "python",
            "args": [
                "mcp_qdrant_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect