How to Use the CDC Public Health / 美国疾控中心 MCP in AutoGen

Q: Can I build a content moderation team for CDC Public Health / 美国疾控中心 media using AutoGen?

Absolutely. Create one agent that finds content with searchhealthmedia and another that critiques it. The agents can debate the relevance and tone of the content before it's approved, simulating a human editorial review process.

Q: What's a good agent setup in AutoGen for checking CDC Public Health / 美国疾控中心 content in multiple languages?

Start with a lead agent that calls listsupportedlanguages. Then, have it spawn a new agent for each language found. Each of these child agents can then be tasked with using searchhealthmedia for its specific language, reporting its findings back to the lead agent.

Assemble teams of AI agents that debate and analyze CDC health data. Use AutoGen's conversational framework to reach consensus.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CDC Public Health / 美国疾控中心 MCP to AutoGen

Create your Vinkius account to connect CDC Public Health / 美国疾控中心 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 CDC Public Health / 美国疾控中心 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up Agent Debates on Health Topics

This server lets your AutoGen agents work together to analyze public health information. Create a 'Researcher' agent that uses `search_health_media` to find content on a given topic, like 'vaccine safety.' Then, add a 'Fact-Checker' agent to the conversation. This agent can use `get_topic_metadata` to retrieve the official CDC guidelines for that topic and challenge the Researcher if the content seems off-message. The agents debate until they agree on the most accurate materials.

Automate Content Strategy with AutoGen

Build a multi-agent workflow for your content pipeline. An 'Analyst' agent can call `get_recent_health_media` to find new content from the CDC. It then presents its findings to the group. A 'Web-Developer' agent in the same chat can then take the proposed media and use `get_syndication_html` to check if it's embeddable. The agents can discuss which pieces are technically suitable and best for your audience, arriving at a group decision.

Coordinate Multi-Language Research

Use an agent team to assess the CDC's international reach. A 'Coordinator' agent starts by calling `list_supported_languages` to see what's available. The Coordinator can then assign a 'Researcher' agent for each language. Each researcher uses `search_health_media` to check content availability in its assigned language and reports back. This conversational approach lets you quickly get a global overview of health communications.

Setup guide

Set up CDC Public Health / 美国疾控中心 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 CDC Public Health / 美国疾控中心 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="CDC Public Health / 美国疾控中心_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CDC Public Health / 美国疾控中心 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="CDC Public Health / 美国疾控中心_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CDC Public Health / 美国疾控中心 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 CDC Public Health / 美国疾控中心. 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 CDC Public Health / 美国疾控中心 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 CDC Public Health / 美国疾控中心 MCP in AutoGen

You assign the tools from this MCP server to different agents with specific roles. For example, give a `UserProxyAgent` the `search_health_media` tool and an `AssistantAgent` the `get_media_details` tool. The first agent can find content, and the second can analyze it, conversing to complete the task.

Absolutely. Create one agent that finds content with `search_health_media` and another that critiques it. The agents can debate the relevance and tone of the content before it's approved, simulating a human editorial review process.

Start with a lead agent that calls `list_supported_languages`. Then, have it spawn a new agent for each language found. Each of these child agents can then be tasked with using `search_health_media` for its specific language, reporting its findings back to the lead agent.

The agents decide based on the ongoing conversation and their assigned roles. When a user or another agent makes a request, the agent with the appropriate tool and instructions will execute it. The framework is designed for this kind of collaborative, conversational tool use.

The server handles public data only—media metadata and topic names from the CDC. Each request you make runs in a fresh, ephemeral container on Vinkius, which is destroyed after the job is done. The agent conversations themselves happen in your AutoGen environment, giving you control over logs.

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