How to Use the Milvus (Open-Source Vector Database) MCP in VS Code Copilot

Q: How does my team share access to Milvus (Open-Source Vector Database) using VS Code Copilot?

You commit the MCP Server configuration to your project's .vscode/mcp.json file. When your team opens the project in VS Code, Copilot automatically connects to the server.

Q: Can VS Code Copilot help me troubleshoot slow queries in Milvus (Open-Source Vector Database)?

Yes. You can ask Copilot to run getcollectionstats to inspect your index sizes and row counts, helping you identify if a collection has grown too large for your current index type.

Q: Can I delete specific test records from my editor?

Yes. You can ask VS Code Copilot to run deleteentities with specific primary keys to remove test records from your development database.

Share Milvus database tools with your entire team using VS Code Copilot and a single config file.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Milvus (Open-Source Vector Database) MCP to VS Code Copilot

Create your Vinkius account to connect Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share Milvus database tools with VS Code Copilot

Run `list_collections` directly from VS Code Copilot to see what vector indices are currently deployed across your environments. Commit your MCP configuration directly to your repository in `.vscode/mcp.json` so every developer on your team gets instant access to your database tools. VS Code Copilot reads this shared configuration to let anyone run database queries without manual setup. This keeps your entire engineering team aligned on the latest database state during collaborative debugging sessions.

Validate vector schemas during code reviews in VS Code

Use VS Code Copilot to run `describe_collection` directly from your editor to inspect production or staging schemas. You can quickly check if a pull request matches the active database schema without opening a separate database client. If you suspect data corruption or indexing issues, have Copilot run `get_collection_stats` to check row counts. This allows your team to spot mismatches using this local MCP Server setup before deploying code.

Verify vector queries and entity retrieval in Copilot Chat

Test your application's search logic by asking VS Code Copilot to run `search_vectors` with sample embedding arrays. Copilot displays the raw similarity scores and matching vector records directly in the chat panel. To inspect specific records, have Copilot run `get_entities` using known primary keys, or use `query_entities` to test complex scalar filters. This ensures your search parameters are correct before you commit your code.

Setup guide

Set up Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) tools listed. Try asking: "List my recent Milvus (Open-Source Vector Database) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "milvus-open-source-vector-database-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 Milvus. 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 Milvus (Open-Source Vector Database) 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 Milvus (Open-Source Vector Database) MCP in VS Code Copilot

You commit the MCP Server configuration to your project's `.vscode/mcp.json` file. When your team opens the project in VS Code, Copilot automatically connects to the server.

Yes. You can ask Copilot to run `get_collection_stats` to inspect your index sizes and row counts, helping you identify if a collection has grown too large for your current index type.

You ask Copilot to run a search in the chat panel. It will call the `search_vectors` tool with your query array and display the matching entities and distance scores.

Yes. You can ask VS Code Copilot to run `delete_entities` with specific primary keys to remove test records from your development database.

No. Your raw vector database content and metadata are queried locally. This MCP Server processes all database connections within your secure network, ensuring your raw embeddings never leave your local environment.

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