How to Use the Zilliz Cloud MCP in AutoGen

Q: If I need to delete data after using Zilliz Cloud and AutoGen?

Use deleteentities when the consensus is reached. This tool lets you surgically remove only the records that are no longer relevant, keeping good data intact.

Q: What should I check before starting a multi-agent task with Zilliz Cloud and AutoGen?

Always run loadcollection first. It pulls the necessary vector store into memory, making it instantly available for all participating agents.

Build consensus-driven decisions by debating results with AutoGen and Zilliz Cloud.

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 AutoGen

Create your Vinkius account to connect Zilliz Cloud to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents debate vector searches via AutoGen

Multiple agents can collaboratively use the `search_vectors` tool. One agent might propose a query, another checks its scope using `describe_collection`, and a third verifies the results against metadata. This conversation forces deliberation: instead of one answer, you get consensus after comparing multiple search outcomes.

Track data flow with AutoGen and MCP Server

When agents work together, they need to track what's happening. You can use `list_collections` to give the entire team a clear view of all available vector stores in Zilliz Cloud. This prevents conflicts because everyone knows which data source the current discussion is referencing.

Manage state with AutoGen

If agents need persistent access to a dataset, they can use `create_collection` and subsequently populate it using `insert_entities`. This establishes a shared, verifiable data source for their debate. The process is robust because the collection's existence is managed by your agent framework.

Setup guide

Set up Zilliz Cloud MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Zilliz Cloud tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Zilliz Cloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zilliz Cloud data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Zilliz Cloud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zilliz Cloud data")
    print(result.messages[-1].content)

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 AutoGen

The agents treat the MCP Server as a source of truth. They debate which tool, like `query_entities`, provides the most reliable data to reach a final conclusion.

It supports complex structured queries, allowing agents to filter results not just by vector similarity but also by specific metadata fields in a collection.

Use `delete_entities` when the consensus is reached. This tool lets you surgically remove only the records that are no longer relevant, keeping good data intact.

Always run `load_collection` first. It pulls the necessary vector store into memory, making it instantly available for all participating agents.

It handles high-dimensional vector embeddings and associated structured metadata. This is the core information that drives multi-agent deliberation.

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