How to Use the Zhumu / 瞩目 MCP in AutoGen

Q: How do I manage Zhumu / 瞩目 meeting changes with AutoGen?

You set up multiple agents. One agent calls updatemeeting and proposes the change, while a second 'Review' agent debates if the new settings meet compliance standards before allowing the update.

Q: Can I list all Zhumu / 瞩目 users for a team audit using AutoGen?

You assign an 'Audit Agent' the listusers tool. This agent collects the entire user roster and then feeds that list to a second 'Reporting Agent' which formats it into the final, readable output.

Run consensus-driven decision making with AutoGen and Zhumu / 瞩目.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zhumu / 瞩目 MCP to AutoGen

Create your Vinkius account to connect Zhumu / 瞩目 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 Zhumu / 瞩目 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiating meeting setup

You build a system where one agent suggests using `create_meeting` while another checks for conflicts via `list_meetings`. They debate the best time slot, and only when they achieve consensus does the final action execute. This simulates real-world scheduling friction.

Validating user permissions

One agent uses `get_user` to fetch details, while a second agent cross-references this data against organizational rules defined in your prompt. They debate if the account is active enough for an action like `update_meeting`, ensuring the final decision is secure.

Reviewing content lifecycle

An 'Auditor' agent calls `list_recordings` to see available videos. A second 'Cleanup' agent determines which recordings are stale or obsolete, debating whether they should be flagged for deletion using `delete_meeting` (if applicable) or archived.

Setup guide

Set up Zhumu / 瞩目 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 Zhumu / 瞩目 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="Zhumu / 瞩目_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Zhumu / 瞩目 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="Zhumu / 瞩目_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Zhumu / 瞩目 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 Zhumu / 瞩目. 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 Zhumu / 瞩目 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 Zhumu / 瞩目 MCP in AutoGen

You set up multiple agents. One agent calls `update_meeting` and proposes the change, while a second 'Review' agent debates if the new settings meet compliance standards before allowing the update.

Yes. The system isn't just about calling tools; it’s about agents discussing the *best* tool call order and arguing over conflicting data points to reach a final, agreed-upon action.

The server handles organizational user records and meeting metadata. When agents debate actions, they are always working with this structured communication data, requiring careful role assignment.

You assign an 'Audit Agent' the `list_users` tool. This agent collects the entire user roster and then feeds that list to a second 'Reporting Agent' which formats it into the final, readable output.

You can build complex pipelines where one agent uses an external API (like a database lookup) and then passes that validated result to the MCP server for final action.

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