How to Use the Zilliz Cloud MCP in Windsurf

Q: How do I query data with Zilliz Cloud in Windsurf?

You use the searchvectors tool. You pass a JSON search configuration describing what you're looking for and how similar it needs to be.

Q: What collections can I see using Zilliz Cloud with Windsurf?

Use the listcollections tool. It returns an inventory of every vector collection managed by your agent within the cluster.

Q: Does Zilliz Cloud support metadata filtering in Windsurf?

Yes, you can filter results using queryentities. This lets your agent narrow down potential hits based on specific data attributes before running the final vector search.

Q: Can I delete a collection from Zilliz Cloud with Windsurf?

Sure. The dropcollection tool completely removes a defined collection, which is useful when you're cleaning up or starting a new project iteration.

Vector search and data management for your Windsurf autonomous workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zilliz Cloud MCP to Windsurf

Create your Vinkius account to connect Zilliz Cloud to Windsurf and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Zilliz Cloud with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage vector collections from a goal.

When you need to set up new data stores, the `create_collection` tool handles it. Just tell Cascade what kind of collection you need and it builds the structure so your agent can start working immediately. It also keeps things clean using `drop_collection`. If a test run fails or you change direction, dropping the old collection ensures your subsequent steps aren't running against stale data.

Run similarity searches with complex filters.

Need to find related documents? Use `search_vectors` for vector similarity search. You provide a JSON search configuration, and the agent executes it across your cluster. Furthermore, if you only want results matching specific criteria, `query_entities` lets you filter by metadata before running the main search. It's powerful stuff for refining outputs.

Monitor and load data stores dynamically.

Before querying anything, check what exists with `list_collections`. This shows your agent every collection available in the Zilliz cluster. If a specific collection is needed for a multi-step process, the agent can use `load_collection` to bring it into memory. It also knows how to clean up using `release_collection`, which keeps your workflow efficient.

Setup guide

Set up Zilliz Cloud 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 Zilliz Cloud 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 Zilliz Cloud payment history." If connected, Cascade will call the Zilliz Cloud tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "zilliz-cloud-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 Zilliz Cloud. 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 Zilliz Cloud 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 Zilliz Cloud MCP in Windsurf

You use the `search_vectors` tool. You pass a JSON search configuration describing what you're looking for and how similar it needs to be.

Use the `list_collections` tool. It returns an inventory of every vector collection managed by your agent within the cluster.

Yes, you can filter results using `query_entities`. This lets your agent narrow down potential hits based on specific data attributes before running the final vector search.

Sure. The `drop_collection` tool completely removes a defined collection, which is useful when you're cleaning up or starting a new project iteration.

The server manages vector collections. When running workflows, the agent interacts with metadata and raw vectors; always ensure your goals are scoped to limit access to sensitive identifiers.

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