Qdrant Logo

Qdrant

Official

Store and retrieve vector-based memories for AI systems.

151 views
2 installs
Updated Nov 22, 2025
Not audited
Store and retrieve vector-based memories for AI systems.
  1. Create or Access a Qdrant Account

    • If you do not have a Qdrant Cloud account, go to the Qdrant Cloud and sign up.
    • Log in to your Qdrant Cloud dashboard.
  2. Create a New Qdrant Cluster or Access an Existing One

    • On the Qdrant Cloud dashboard, either create a new cluster or select an existing one you wish to use.
    • Copy the HTTPS endpoint URL for this cluster (it looks like https://xyz-example.region.aws.cloud.qdrant.io:6333).
  3. Obtain an API Key for Your Qdrant Cluster

    • In the sidebar, navigate to the “API Keys” section (sometimes called “API Access”).
    • Click “Generate API Key” or “Create New Key”.
    • Optionally, provide a name and select the desired permissions (Read/Write or as required).
    • Save the generated API key securely. You will need it for configuration.
  4. Choose or Create a Collection Name

    • Decide on a collection name for storing your vectors (e.g., my-collection). This can be any string and will be used to organize your data.
    • You can use an existing collection name or specify a new one; mcp-server-qdrant will create it if it does not exist.
  5. (Optional) Decide on an Embedding Model

    • By default, sentence-transformers/all-MiniLM-L6-v2 is used.
    • You can change the model if needed, but for most users, the default is sufficient.
  6. Fill In the FastMCP Connection Interface

    • Click the Install Now button in your environment to open the FastMCP connection interface.
    • In the fields provided, enter:
      • QDRANT_URL: Your cluster URL from step 2, e.g., https://xyz-example.region.aws.cloud.qdrant.io:6333
      • QDRANT_API_KEY: Your API key from step 3
      • COLLECTION_NAME: The collection name you chose in step 4
      • (Optional) EMBEDDING_MODEL: Change only if you wish to use a different model.
  7. Save and Complete the Setup

    • Confirm and save your configuration in the FastMCP connection interface.
    • You are now ready to use the Qdrant MCP server with your specified settings.

Note:

  • If you are using a local Qdrant server instead of Qdrant Cloud, set QDRANT_URL to your local Qdrant endpoint (e.g. http://localhost:6333).
  • For local mode, you may omit QDRANT_API_KEY if authentication is not enabled and set QDRANT_LOCAL_PATH instead if running Qdrant locally.

Quick Start

View on GitHub

More for Memory Management

View All →

More for Database

View All →

Similar MCP Servers

A

AI Memory

Production-ready semantic memory management server that stores, retrieves, and manages contextual knowledge across sessions using PostgreSQL with pgvector for vector similarity search, featuring intelligent caching, multi-user support, memory relationships, automatic clustering, and background job processing for persistent AI memory and knowledge management systems.

Memory Management AI and Machine Learning
286
0

Report Issue

Thank you! Your issue report has been submitted successfully.