How do I connect this MCP to my Zilliz cluster?

You need to provide your Zilliz Cluster Endpoint and your API Key during the setup process in Vinkius.

Which AI clients can I use with this MCP?

You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I manage cluster resources through my AI agent?

Yes, you can use the load and release capabilities to manage how collections occupy cluster memory.

Does this MCP support metadata filtering?

Yes, the query_entities capability allows you to find specific records using boolean expressions and metadata filters.

Is it possible to delete data using this MCP?

Yes, you can use the delete_entities capability to remove specific records or the drop_collection capability to remove entire collections.

How do I find my Cluster Endpoint?

You can find your Cluster Endpoint in the Zilliz Cloud Console under the 'Cluster Details' page. It typically looks like https://in01-xxxxxxxxxxxx.vectordb.zillizcloud.com.

Why do I need to 'load' a collection before searching?

Zilliz requires collections to be loaded into memory to perform high-performance similarity searches. Use the load_collection capability to make your data available for search.

Can I filter my vector search using metadata?

Yes, Zilliz supports hybrid search. You can use the query_entities capability for metadata-only filtering or include filtering expressions in your search_vectors JSON configuration.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Zilliz Cloud to ChatGPT, Claude and Gemini

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. Run similarity searches and manage collections through natural language.

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.

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.

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 · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Zilliz Cloud.

01
Create collection
This capability creates a new vector collection in your Zilliz cluster using a JSON body.
02
Describe collection
This capability retrieves the schema and configuration details for a specific collection.
03
Drop collection
This capability permanently removes a collection from your cluster.
04
Insert entities
This capability adds new vector and scalar data into a designated collection.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Zilliz Cloud.

05
List collections
This capability returns a list of all collections currently in your Zilliz cluster.
06
Query entities
This capability finds specific records by applying metadata filters and boolean expressions.
07
Release collection
This capability removes a collection from memory to free up cluster resources.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Zilliz Cloud.

08
Delete entities
This capability removes specific entities from an existing collection.
09
Load collection
This capability loads a collection into memory to make it available for searching.
10
Search vectors
This capability performs vector similarity searches based on a JSON search configuration.

Real work

What teams actually run

Rapid Prototyping

Quickly spin up new collections to test how different vector dimensions behave.

Resource Optimization

Tell your agent to release unused collections to keep the cluster running efficiently.

Data Auditing

Use the agent to check collection schemas and row counts instantly.

Automated Retrieval

Let your agent handle the heavy lifting of similarity searches during application development.

Automate a task

Put Zilliz Cloud 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

Zilliz Cloud 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.

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

You don't need a client to put Zilliz Cloud 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

968ms average. Fast in production.

Zilliz Cloud is checked daily against the live service.

Daily averagePeak 1190ms

Oct 3Today

Fastest day: 790ms
Slowest day: 1190ms
14-day trend: Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 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 Zilliz Cloud, so you can see the experience inside your AI.

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

Zilliz Cloud Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_RKv8SXkDaOvT7RS1nwfoO7ZP8GbUdouO1cKQtzMb/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Zilliz Cloud capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "zilliz-cloud-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_RKv8SXkDaOvT7RS1nwfoO7ZP8GbUdouO1cKQtzMb/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 Zilliz Cloud in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Zilliz Cloud owners hand off.

This MCP is built for technical professionals working with high-dimensional data and vector databases.

01
AI Engineers
They use the MCP to test vector searches and verify schemas through natural language.
02
Data Scientists
They monitor cluster health and data distribution without writing boilerplate code.
03
Developers
They integrate vector retrieval and management directly into their coding workflows.

FAQ

Questions Zilliz Cloud owners ask.

01
How do I connect this MCP to my Zilliz cluster?
You need to provide your Zilliz Cluster Endpoint and your API Key during the setup process in Vinkius.
02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can I manage cluster resources through my AI agent?
Yes, you can use the load and release capabilities to manage how collections occupy cluster memory.
04
Does this MCP support metadata filtering?
Yes, the query_entities capability allows you to find specific records using boolean expressions and metadata filters.
05
Is it possible to delete data using this MCP?
Yes, you can use the delete_entities capability to remove specific records or the drop_collection capability to remove entire collections.
06
How do I find my Cluster Endpoint?
You can find your Cluster Endpoint in the Zilliz Cloud Console under the 'Cluster Details' page. It typically looks like https://in01-xxxxxxxxxxxx.vectordb.zillizcloud.com.
07
Why do I need to 'load' a collection before searching?
Zilliz requires collections to be loaded into memory to perform high-performance similarity searches. Use the load_collection capability to make your data available for search.
08
Can I filter my vector search using metadata?
Yes, Zilliz supports hybrid search. You can use the query_entities capability for metadata-only filtering or include filtering expressions in your search_vectors JSON configuration.

Explore

More in AI Frontier

Connect Zilliz Cloud to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create collection

Describe collection

Drop collection

Insert entities

05-07

List collections

Query entities

Release collection

08-10

Delete entities

Load collection

Search vectors

What teams actually run

Rapid Prototyping

Resource Optimization

Data Auditing

Automated Retrieval

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

Zilliz Cloud Connector

Claude Desktop

AI Engineers

Data Scientists

Developers

How do I connect this MCP to my Zilliz cluster?

Which AI clients can I use with this MCP?

Can I manage cluster resources through my AI agent?

Does this MCP support metadata filtering?

Is it possible to delete data using this MCP?

How do I find my Cluster Endpoint?

Why do I need to 'load' a collection before searching?

Can I filter my vector search using metadata?

Milvus (Open-Source Vector Database) AI Connector

DataStax Astra DB Vector AI Connector

Typesense Vector Search AI Connector

MongoDB Atlas Vector Search AI Connector

Suggestions

Marqo AI (Vector Search & Embeddings) AI Connector

pgvector (Vector Database) AI Connector

Qdrant AI Connector

JD Cloud Infrastructure AI Connector