An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Milvus Open Source Vector Database to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your high-performance vector database through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Milvus.

  1. 01

    List collections

    This capability lists all the index collections currently stored in your Milvus database. It is the best place to start when you need to see what data is available.

  2. 02

    Describe collection

    Use this to pull the specific schema and indexing definitions for a collection. It shows you the field mappings and how your data is structured.

  3. 03

    Get entities

    This capability retrieves specific vector items using their primary keys. It allows you to pull exact data points without running a full search.

  4. 04

    Delete entities

    This capability removes specific vector records from your database. You must provide the primary keys to perform this permanent deletion.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Milvus.

  1. 05

    Get collection stats

    Get real-time statistics for a collection. It returns the total row counts to help you monitor your data volume.

  2. 06

    Query entities

    This capability lets you filter and retrieve data using scalar expressions. You can use it to find entities based on structured fields like IDs or tags.

  3. 07

    Search vectors

    Perform similarity searches by providing a JSON array of vectors. The agent uses these to find the nearest neighbors in your collection.

Real work

What teams actually run

01

Embedding Debugging

Quickly check if your vector dimensions match your expected model output.

02

Database Auditing

Verify the schema and index types of your collections during development.

03

Data Maintenance

Clean up old or incorrect vector records using primary key deletions.

04

Retrieval Testing

Test how different scalar filters affect your similarity search results.

Automate a task

Put Milvus to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Milvus works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Milvus to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

926ms average. Fast in production.

Milvus is checked daily against the live service.

Daily averagePeak 1112ms
Oct 3Today
Fastest day
689ms
Slowest day
1112ms
14-day trend
Improving-13%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Milvus, so you can see the experience inside your AI.

It does not authenticate your account with Milvus. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Milvus Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xJCavC8CNaxFuBWU15XnlYyQ3g4Cn853dcyYbM82/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Milvus capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "milvus-open-source-vector-database-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xJCavC8CNaxFuBWU15XnlYyQ3g4Cn853dcyYbM82/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Milvus in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Milvus owners hand off.

This MCP is built for technical professionals managing high-dimensional data who want to move faster.

  • 01

    ML Engineers

    They use the agent to verify embedding dimensions and test vector relevance without writing scripts.

  • 02

    Search Architects

    They use the agent to audit collection schemas and monitor indexing performance.

  • 03

    Software Developers

    They use the agent to manage vector lifecycles across different environments.

FAQ

Questions Milvus owners ask.

  • 01

    How do I connect my Zilliz Cloud account?

    You simply enter your Zilliz Cloud Token in the configuration settings after subscribing to the MCP.

  • 02

    Can I use this with my local Milvus instance?

    Yes, just provide the Base URL for your local instance during the setup process.

  • 03

    What clients are compatible with this MCP?

    This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 04

    Does this MCP support scalar filtering?

    Yes, you can use the query_entities capability to filter data using structured scalar expressions.

  • 05

    Is the data deletion permanent?

    Yes, using the delete_entities capability to remove records via primary keys is an irreversible action.

  • 06

    How do I perform an ANN search through my agent?

    Use the search_vectors capability by providing the collection name and a JSON float array matching the collection's dimensions. Your agent will perform an Approximate Nearest Neighbor search and return the most semantically relevant entities.

  • 07

    Can I filter results using structured fields instead of just vectors?

    Yes. Use the query_entities capability with a Milvus-style filter expression. This allows you to retrieve entities based on primary keys, tags, or other scalar fields without necessarily performing a vector similarity search.

  • 08

    How do I check the schema and dimension requirements for a Milvus collection?

    The describe_collection capability retrieves the complete schema mapping. Your agent will report the required vector dimensions, index types, and primary key names, helping you ensure your search queries are compatible with the database logic.

Explore

More in Loved By Devs

Suggestions

Connect Milvus to Claude, Cursor, ChatGPT & more