How to Use the Zilliz Cloud MCP in VS Code Copilot

Q: How does VS Code Copilot use Zilliz Cloud for team data context?

The MCP configuration lives in .vscode/mcp.json and is committed to the repo, ensuring every developer sees the same tools. When needed, Copilot calls searchvectors, pulling live context into the code editor.

Q: Can I define a new vector collection using Zilliz Cloud and VS Code Copilot?

Yes. You can use createcollection to build out necessary indexes as part of your team's infrastructure setup. Once the schema is defined, it’s available for all developers.

Q: What process should we follow to check collection availability with Zilliz Cloud and VS Code Copilot?

Run listcollections first. This gives the entire team a single source of truth regarding which vector indexes are currently active in the cluster, keeping everyone aligned.

Q: Is it possible to use Zilliz Cloud and VS Code Copilot for advanced data querying?

Absolutely. Use queryentities when you need to filter your search results using specific metadata criteria. This narrows the scope of the query, improving code accuracy.

Ensure every developer uses consistent vector context with VS Code Copilot's team configuration.

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 VS Code Copilot

Create your Vinkius account to connect Zilliz Cloud to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce shared data access across the entire engineering team.

The team can commit `mcp.json` to the repository, making Zilliz Cloud accessible via VS Code Copilot for every developer. This means everyone works with the same, version-controlled context. You use this consistency to prevent developers from accidentally referencing stale or different data sources.

Manage and audit vector collection definitions.

Before a feature lands in code, verify the required structure. Use `list_collections` across the team to confirm all necessary indexes are present. If you need details on one, `describe_collection` provides that documentation. This ensures new hires or rotating members can immediately understand the data landscape.

Execute reliable, complex similarity searches for shared context.

When a teammate needs specific external knowledge, they run `search_vectors`. This tool performs vector similarity search and returns highly relevant results that Copilot uses to write accurate code blocks. This centralization of the search function keeps the codebase predictable.

Setup guide

Set up Zilliz Cloud MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Zilliz Cloud MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Zilliz Cloud tools listed. Try asking: "List my recent Zilliz Cloud transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

The MCP configuration lives in `.vscode/mcp.json` and is committed to the repo, ensuring every developer sees the same tools. When needed, Copilot calls `search_vectors`, pulling live context into the code editor.

Yes. You can use `create_collection` to build out necessary indexes as part of your team's infrastructure setup. Once the schema is defined, it’s available for all developers.

Run `list_collections` first. This gives the entire team a single source of truth regarding which vector indexes are currently active in the cluster, keeping everyone aligned.

Absolutely. Use `query_entities` when you need to filter your search results using specific metadata criteria. This narrows the scope of the query, improving code accuracy.

This server touches structured data (entities) and vector embeddings. By managing configuration via a committed file, you ensure that the access to this sensitive context is auditable and consistent across your entire engineering team.

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