Qdrant Vector Database MCP server

Integrates with Qdrant vector database to provide semantic search capabilities for storing and retrieving information using multiple embedding providers, deployable via Docker or locally.
Back to servers
Provider
Jimmy974
Release date
Mar 18, 2025
Language
Python

The MCP Server for Qdrant provides a Machine Control Protocol server that allows you to store and semantically search information in a Qdrant vector database. It integrates with FastEmbed for text embeddings and offers both local and Docker deployment options.

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 managed through environment variables. You can create a .env file based on the provided example:

cp .env.example .env

Edit the .env file with your specific settings:

# 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

Running the Server

Local Execution

Run the server directly with Python:

python -m mcp_server_qdrant.main

Or use the make command if available:

make run

Using Docker

For containerized deployment:

docker-compose up

Available Tools

The MCP server exposes two main tools for interacting with the Qdrant database:

qdrant-store

This tool stores text information in the Qdrant database with optional metadata.

Parameters:

  • information: The text content to store
  • metadata: Optional JSON metadata to associate with the text

qdrant-find

This tool performs semantic search to find relevant information in the database.

Parameters:

  • query: The search query text to find semantically similar content

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later