How to Use the Qdrant MCP in Windsurf

Q: How do I perform a similarity search in Qdrant using Windsurf?

You trigger the search tool by passing your query vector as a JSON array of floats. Windsurf will then return the nearest neighbors based on your vector distance settings.

Q: Can Windsurf delete points from Qdrant directly?

Yes, but be careful. Using the delete tool is irreversible and removes the specified points from your collection immediately.

Q: Does this Qdrant MCP Server allow Windsurf to list all collections?

It does. You can call listcollections to see every index currently hosted in your instance.

Q: What is the best way to iterate through data in Qdrant with Windsurf?

Use the scroll tool. It allows you to paginate through your points and their payloads, which is much more efficient than fetching them one by one.

Use the Qdrant MCP Server to let Windsurf query your vector database and manage collections directly from the IDE.

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 Windsurf

Create your Vinkius account to connect Qdrant to Windsurf — 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and fetch data with Windsurf

Cascade uses `search` to run nearest neighbor lookups across your vector space. It pulls the most relevant results for your current coding task without manual intervention. You can also use `get_points` to pull exact records by ID. Windsurf handles the data mapping so you can focus on the logic.

Manage collections inside your MCP Server

List your active collections using `list_collections` to see what is currently indexed. It gives you a clear view of your database structure without leaving your workspace. Need more detail? The `get_collection` tool pulls the status and configuration of any specific set. It keeps your context accurate.

Paginate records with scroll

The `scroll` tool lets you iterate through large datasets by fetching points with their payloads. It is the right way to handle batch processing when you need to audit your entire index. Use `count` to verify the total volume of points in a collection. It helps you keep track of your data footprint as your project grows.

Setup guide

Set up Qdrant MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Qdrant MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Qdrant payment history." If connected, Cascade will call the Qdrant tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

You trigger the `search` tool by passing your query vector as a JSON array of floats. Windsurf will then return the nearest neighbors based on your vector distance settings.

Yes, but be careful. Using the `delete` tool is irreversible and removes the specified points from your collection immediately.

It does. You can call `list_collections` to see every index currently hosted in your instance.

Use the `scroll` tool. It allows you to paginate through your points and their payloads, which is much more efficient than fetching them one by one.

The server only touches the specific vector points and collection metadata you query. It operates within your local environment and requires no external data sharing.

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