How to Use the Milvus (Open-Source Vector Database) MCP in Claude

Get exact vector search results directly inside Claude Desktop without leaving your chat window.

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 Claude Desktop

Create your Vinkius account to connect Milvus (Open-Source Vector Database) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Explore Milvus collections inside Claude Desktop

Run `list_collections` right from your Claude Desktop chat box to see what vector spaces are active on your local machine. Claude Desktop parses these Milvus collections directly into your chat window without forcing you to open a separate terminal. Once you find the collection you need, use `describe_collection` to inspect its schema and index types. Claude Desktop renders the raw JSON output into a clean summary so you can check dimension counts and distance metrics instantly.

Run vector searches directly in your desktop chat

Provide raw text to Claude Desktop and let your agent convert it to embeddings to run `search_vectors` against your local Milvus instance. You get the closest vector matches returned straight into your conversation window, complete with similarity scores. If you need to narrow down the results, have Claude Desktop trigger `query_entities` with scalar filters. This lets you isolate specific partitions or metadata fields without writing complex Python scripts or manual SDK calls.

Manage vector records using this MCP Server

Clean up bad data or old test runs by letting Claude Desktop execute `delete_entities` using primary keys. You can identify the target records first by calling `get_entities` to make sure you have the right IDs before making any permanent changes. This MCP Server runs as a local subprocess on your machine, giving Claude Desktop direct, secure access to your Milvus instance. You get fast feedback loops during development without exposing your database to external networks.

Setup guide

Set up Milvus (Open-Source Vector Database) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Milvus (Open-Source Vector Database) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Milvus (Open-Source Vector Database) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under milvus-open-source-vector-database-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 Claude Desktop

You just paste your query text or raw array into the chat. Claude Desktop uses the `search_vectors` tool to query your Milvus instance and prints the nearest neighbors with their similarity scores.

Yes. Ask Claude Desktop to check your collections, and it will run `list_collections` followed by `describe_collection` to show you the exact schema and vector dimensions in your chat.

Yes, you configure this MCP Server by adding its command and arguments to your `claude_desktop_config.json` file. Once saved, restart Claude Desktop, and the database tools will appear under the hammer icon in your chat input.

Tell your agent what metadata filters you want to apply. Claude Desktop will execute `query_entities` with your scalar expressions to filter the Milvus records before displaying them.

Your raw text embeddings and vector metadata stay on your local machine. Claude Desktop communicates with the local database over a secure stdio transport layer, meaning your database contents never touch external third-party servers.

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