How to Use the Zilliz Cloud MCP in Mastra AI

Q: How does Mastra AI handle vector searches with Zilliz Cloud?

Mastra AI executes the search via searchvectors. The workflow engine treats the returned data as a critical state variable, allowing subsequent steps to process or validate the results automatically.

Q: Can I manage multiple vector indexes with Zilliz Cloud and Mastra AI?

You can use listcollections to map out your entire data landscape. The framework allows you to cycle through different collections, managing context using tools like loadcollection for each distinct workflow phase.

Build complex, resilient workflows using Mastra AI's advanced MCP Server capabilities.

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 Mastra AI

Create your Vinkius account to connect Zilliz Cloud to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Vector Search in Mastra AI

When a workflow needs contextual knowledge, it calls `search_vectors`. The result isn't just data; it’s an input that drives the next step of your process. Your agent framework can conditionally branch based on the similarity scores found by Zilliz Cloud. This means you build resilience into the search itself. If the initial query fails, Mastra AI handles retries with exponential backoff until a viable set of vectors is retrieved.

Manage Search Context in Mastra AI

Before running complex steps, your workflow needs clean data. Use `list_collections` to identify the correct source and then `describe_collection` for validation. This ensures that when you call `query_entities`, you're targeting the right set of stored information. Developers can also `load_collection` into memory explicitly, guaranteeing all necessary vector context is available for the entire multi-step process.

Ensure Data Integrity with Mastra AI

Mastra AI workflows must be reliable. You maintain data integrity by using `insert_entities` to add records and, if needed, calling `delete_entities` or `drop_collection`. This granular control ensures your workflow always operates on the most accurate source of truth. If a search needs refinement, you can use `query_entities` combined with metadata filtering to narrow down results precisely.

Setup guide

Set up Zilliz Cloud MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Zilliz Cloud tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "zilliz-cloud-mcp-client",
  servers: {
    "zilliz-cloud-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Zilliz Cloud Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Zilliz Cloud tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Zilliz Cloud transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI executes the search via `search_vectors`. The workflow engine treats the returned data as a critical state variable, allowing subsequent steps to process or validate the results automatically.

Yes. Mastra AI's built-in engine supports automatic retries and conditional branching. If a search fails, it doesn't halt; it tries an alternate method or notifies the admin.

You can use `list_collections` to map out your entire data landscape. The framework allows you to cycle through different collections, managing context using tools like `load_collection` for each distinct workflow phase.

The MCP Server operates within a zero-trust V8 Isolate Sandbox environment. Authentication is handled via an endpoint token, keeping your complex multi-step processes isolated and secure.

This server manages vector collections and entities. The specific data types involved are the vectors themselves, along with associated metadata used for filtering during searches or queries.

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