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

Q: How do I chain CDC Public Health / 美国疾控中心 topic searches with LangChain?

You create an agent and give it both the listhealthtopics and searchhealthmedia tools. The agent can then decide to call the first tool to get topics, then use an output from that list to call the second tool. LangChain's ReAct framework handles this reasoning loop.

Q: Can my LangChain agent get embeddable content from CDC Public Health / 美国疾控中心?

Yes. Once your agent finds a piece of media using searchhealthmedia, it can pass that item's ID to the getsyndicationhtml tool. This tool returns the exact HTML snippet needed to embed the content on a webpage.

Q: How does LangChain handle multiple results from the CDC Public Health / 美国疾控中心 server?

When a tool like searchhealthmedia returns a list of items, your LangChain agent can iterate over that list. You can design chains that process each item individually, for example, by calling getmediadetails for every result.

Build agents that reason through public health data. Connect LangChain to the official CDC media API and create multi-step analysis chains.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain CDC Tools for Deeper Analysis

Your agent can now run sequences of queries against CDC data. Start by calling `list_health_topics` to get a full list of official subjects. Then, feed a specific topic into `search_health_media` to find all related content. This isn't just a single API call. It's a chain of reasoning. The output of one tool becomes the input for the next, letting your agent explore the data just like a human would. LangSmith gives you a full trace of the agent's decisions.

Automate Content Syndication

Build a chain that keeps your health content fresh. Your agent can periodically call `get_recent_health_media` to check for new articles or videos from the CDC. For each new item, a subsequent step in the chain calls `get_syndication_html` to grab the correct embed code. You can pipe this directly into a CMS or a content deployment script. It's a simple, reliable way to republish official health information.

Research Health Topics with LangChain

Give your agent the tools for focused research. The `search_hhs_resources` tool lets it query the entire HHS Digital Media library by keyword for a broad search. Then, your agent can refine the results. It can take the most relevant IDs and pass them to `get_media_details` to pull specific metadata like publication dates and formats. This is how you build an agent that gathers and organizes information, not just fetches it.

Setup guide

Set up CDC Public Health / 美国疾控中心 MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CDC Public Health / 美国疾控中心 tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "cdc-public-health-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CDC Public Health / 美国疾控中心 transactions"
    })
    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 LangChain

You create an agent and give it both the `list_health_topics` and `search_health_media` tools. The agent can then decide to call the first tool to get topics, then use an output from that list to call the second tool. LangChain's ReAct framework handles this reasoning loop.

Yes. Once your agent finds a piece of media using `search_health_media`, it can pass that item's ID to the `get_syndication_html` tool. This tool returns the exact HTML snippet needed to embed the content on a webpage.

Use LangSmith. Every tool call made through this MCP Server, including inputs and outputs, is automatically traced. This lets you see exactly what your agent is doing, how long each step takes, and why it's making its decisions.

When a tool like `search_health_media` returns a list of items, your LangChain agent can iterate over that list. You can design chains that process each item individually, for example, by calling `get_media_details` for every result.

The agent only interacts with public health media metadata and topic lists. The Vinkius platform processes each tool call in a sandboxed, ephemeral environment. Your LangChain agent simply passes this public data through its chain; no private information is ever requested or stored by the server.

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