How to Use the Qdrant MCP in Cursor

Q: How does the Cursor agent execute a similarity search on Qdrant?

The Cursor agent calls the search tool using a float array representing your query vector. It pulls the closest matches directly into your workspace to help you write accurate RAG logic.

Q: Can I use Cursor to paginate through my Qdrant vectors?

Yes, you can. Cursor uses the scroll tool to page through your vectors and payloads, letting you inspect database contents directly in the editor.

Q: Does Cursor support managing multiple Qdrant collections?

Yes, it does. Cursor uses listcollections to show you every index in your database, letting you switch contexts or query different models on the fly.

Q: What happens if a vector search fails during a Cursor session?

If the search tool returns a low confidence score, your agent can fallback to using scroll to inspect the raw points and diagnose why the HNSW index missed the match.

Generate working code with live vector data by connecting Qdrant directly to your Cursor agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Qdrant MCP to Cursor

Create your Vinkius account to connect Qdrant to Cursor — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Qdrant with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Vector Context for Cursor Code Generation

This MCP Server brings the Qdrant `search` tool into your Cursor workspace so your agent can run actual queries against your live database while writing code. By feeding real nearest-neighbor results back into the LLM context, the code generated is tailored to your actual data schema. You get working implementation code instead of placeholder templates that break on deployment. It stops you from writing code against stale mock data.

Inspect Qdrant Collections Inside Cursor

Your agent runs the `list_collections` tool inside Cursor to check if your vector database ingested your embeddings correctly. If you suspect a bad batch of embeddings, your agent can run `get_points` to verify the exact float values and payload keys. This immediate feedback loop cuts down the time spent debugging malformed vector structures. You don't have to jump to external GUI tools.

Data Cleanup and Verification

Your Cursor agent uses the `delete` tool to wipe specific test points from your Qdrant collection during local development. To verify the collection state after a deletion, the agent runs `count` to confirm the exact point density. This ensures your index size matches your code's expectations before you push your changes to staging. It keeps your local database clean while you iterate on embedding pipelines.

Setup guide

Set up Qdrant MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Qdrant MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Qdrant transactions." If the MCP tools are loaded correctly, Cursor will call the Qdrant tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "qdrant-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Qdrant. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Qdrant now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Qdrant MCP in Cursor

The Cursor agent calls the `search` tool using a float array representing your query vector. It pulls the closest matches directly into your workspace to help you write accurate RAG logic.

Yes, you can. Cursor uses the `scroll` tool to page through your vectors and payloads, letting you inspect database contents directly in the editor.

Yes, it does. Cursor uses `list_collections` to show you every index in your database, letting you switch contexts or query different models on the fly.

If the `search` tool returns a low confidence score, your agent can fallback to using `scroll` to inspect the raw points and diagnose why the HNSW index missed the match.

Your Qdrant vector payloads and float arrays are transmitted over encrypted TLS directly through the Vinkius MCP sandbox. No database records or embedding parameters are cached on Cursor servers, keeping your index private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript