Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Qdrant with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Empower your AI to interact directly with your Qdrant vector database. query clusters, perform similarity searches, and manage collections effortlessly.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 7 capabilities

The complete Qdrant capability set.

These are the exact actions your AI can choose when you ask it to work with Qdrant.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Qdrant.

  1. 01

    Count

    Counts the total number of points in a collection

  2. 02

    Delete

    This action is irreversible. Deletes specific points from a collection

  3. 03

    Get collection

    Retrieves detailed information about a specific collection

  4. 04

    Get points

    Retrieves specific points by their IDs

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Qdrant.

  1. 05

    List collections

    Lists all collections in the Qdrant instance

  2. 06

    Search

    You must provide a JSON array of floats for the query vector. Performs a nearest neighbor vector search in a collection

  3. 07

    Scroll

    Returns points with their payloads. Scrolls through points in a collection, useful for pagination

Observed, not estimated

884ms average. Fast in production.

Qdrant is checked daily against the live service.

Daily averagePeak 1067ms
Aug 20Today
Fastest day
718ms
Slowest day
1067ms
14-day trend
Slowing+38%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Qdrant, so you can see the experience inside your AI.

It does not authenticate your account with Qdrant. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Qdrant Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_q8RmctE5Ixu7FdouvzysiVBMHUlpWlDBAdtwVmus/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Qdrant capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "qdrant-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_q8RmctE5Ixu7FdouvzysiVBMHUlpWlDBAdtwVmus/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Qdrant owners ask.

  • 01

    How do I find my Qdrant URL and API Key?

    For Qdrant Cloud: Go to the Qdrant Cloud Console, select your cluster to open the Cluster Detail Page. The endpoint will be displayed there (e.g., xyz.us-east4-0.gcp.cloud.qdrant.io), and you can generate Database API Keys underneath it (they start with eyJhb). For Self-hosted: Provide your custom URL and the static custom key you defined in your config.yaml.

  • 02

    Can my AI use this for a RAG architecture directly?

    Yes contextually, but practically your agent acts as the database debugger. It can formulate vector arrays to query search_points, retrieving identical payload structures. It's meant for the engineer building the RAG, helping you inspect distances and debug faulty retrieval mechanisms mid-code.

  • 03

    Does it support deleting vectors?

    Yes. If an embedding got corrupted or references dropped articles, use the delete capability. Pass the collection name and the list of specific IDs. Qdrant handles the mutation instantly and updates the index without rebuilding.

  • 04

    What if I have millions of points?

    Instead of overloading your chat context, instruct your agent to use the count capability to grasp the scale, and the scroll capability with a small limit constraint (e.g., 5-10 records at a time). This paginates large bodies cleanly when analyzing index health.

Explore

More in AI Frontier

Suggestions