Qdrant MCP Server

What does “Qdrant” MCP Server do?

The Qdrant MCP Server is an official implementation of the Model Context Protocol (MCP) for the Qdrant vector search engine. Acting as a semantic memory layer, it allows AI assistants and LLM-powered applications to store and retrieve information within the Qdrant database. By exposing standardized MCP endpoints, the server enables seamless integration with external data sources, thus enhancing AI development workflows. Developers can leverage it to run vector-based queries, manage collections, and handle semantic memory for AI agents, making it ideal for tasks like knowledge retrieval, contextual memory storage, and advanced search operations in their applications.

List of Prompts

No information about prompt templates is provided in the repository or documentation.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit resources are documented or listed in the repository or documentation.

List of Tools

• qdrant-store
  • Stores information in the Qdrant database. Accepts a string of information, optional metadata, and a collection name. Returns a confirmation message.
• qdrant-find
  • Retrieves relevant information from the Qdrant database using a search query and a collection name. Returns stored information as separate messages.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Semantic Memory for AI Agents: Store contextual data and retrieve it as needed, enabling AI agents to remember past interactions and use them for more informed responses.
• Knowledge Base Search: Allow developers to build knowledge retrieval systems where users can search for relevant documentation, support content, or FAQs using semantic queries.
• Personalized Recommendations: Use stored user interaction data to generate recommendations or insights based on semantic similarity.
• Contextual Chatbots: Enhance chatbots by giving them access to a semantic memory layer, letting them reference past conversations or related information dynamically.

How to set it up

Windsurf

1. Ensure you have the prerequisites installed (e.g., Node.js).
2. Locate your Windsurf configuration file.
3. Add the Qdrant MCP Server configuration in the mcpServers object:

   {
     "mcpServers": {
       "qdrant-mcp": {
         "command": "qdrant-mcp-server",
         "args": []
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the setup by checking for successful connection to the MCP server.

Claude

1. Install prerequisites as specified by Claude’s documentation.
2. Edit the Claude configuration file.
3. Add Qdrant MCP Server settings to the mcpServers section:

   {
     "mcpServers": {
       "qdrant-mcp": {
         "command": "qdrant-mcp-server",
         "args": []
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm the configuration by testing an MCP operation.

Cursor

1. Confirm all required dependencies are installed.
2. Open the Cursor configuration.
3. Insert the following snippet to register the Qdrant MCP Server:

   {
     "mcpServers": {
       "qdrant-mcp": {
         "command": "qdrant-mcp-server",
         "args": []
       }
     }
   }
   

4. Save and restart Cursor.
5. Check server logs for a successful connection.

Cline

1. Set up prerequisites as per Cline’s requirements.
2. Find and open the relevant configuration file.
3. Add the MCP server to your configuration:

   {
     "mcpServers": {
       "qdrant-mcp": {
         "command": "qdrant-mcp-server",
         "args": []
       }
     }
   }
   

4. Save and restart Cline.
5. Test the connection and functionality.

Securing API Keys using Environment Variables

Set required environment variables to secure your API keys. Example JSON configuration:

{
  "mcpServers": {
    "qdrant-mcp": {
      "command": "qdrant-mcp-server",
      "args": [],
      "env": {
        "QDRANT_URL": "https://your-qdrant-server.example",
        "QDRANT_API_KEY": "your_qdrant_api_key"
      },
      "inputs": {
        "COLLECTION_NAME": "your_default_collection"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "qdrant-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “qdrant-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the Qdrant MCP Server is solid for its core functionality and setup clarity but lacks detailed prompt and resource documentation. It scores high for tool support and licensing, but more user guidance and advanced features would be beneficial.

MCP Score

MCP Table Score: 7/10

The Qdrant MCP Server provides clear core functionality, a proper license, and robust tool support. However, the absence of prompt/resource documentation and unclear advanced feature support prevents a higher score.