How to Use the CDC WONDER (Epidemiologic Data) MCP in Pydantic AI

Q: How do I install CDC WONDER (Epidemiologic Data) for Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Create an MCPToolset using the unified HTTP approach with your Vinkius URL, then pass it to your Agent's toolsets parameter.

Q: Does Pydantic AI still use MCPServerHTTP for this connection?

No. That class is deprecated. You must use the MCPToolset wrapper to configure this MCP connection to external servers running via Streamable HTTP or SSE transports.

Build reliable public health pipelines. Pydantic AI enforces strict runtime validation on every CDC WONDER query your agent makes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CDC WONDER (Epidemiologic Data) MCP to Pydantic AI

Create your Vinkius account to connect CDC WONDER (Epidemiologic Data) to Pydantic 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 CDC WONDER (Epidemiologic Data) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe public health data extraction

Epidemiological data is useless if the formatting is wrong. Pydantic AI forces every response from the `query_wonder_database` tool into strict Python models via the MCP standard. If the CDC API returns an unexpected string instead of a mortality count, the framework fails loudly. Your agent catches the validation error immediately instead of passing corrupted numbers downstream into your analysis.

Model-agnostic CDC WONDER MCP Server queries

Locking into a specific LLM provider for health research is risky. Pydantic AI lets you swap between OpenAI, Anthropic, or local models while keeping the exact same data extraction logic intact. Setup requires initializing the toolset with your Vinkius HTTP endpoint and passing it to the Agent constructor. The framework handles the translation layer, ensuring the active model always formats the B_ and M_ prefixed parameters correctly.

Prevent hallucinated database IDs

Language models love to guess API parameters when they get confused. This setup prevents your agent from inventing fake CDC database codes or malformed JSON payloads. The framework validates the inputs before the `query_wonder_database` call even fires. You get absolute certainty that your agent is requesting real demographic segments from real databases like D76.

Setup guide

Set up CDC WONDER (Epidemiologic Data) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cdc-wonder-epidemiologic-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CDC WONDER (Epidemiologic Data) tools.",
)

result = await agent.run("List recent CDC WONDER (Epidemiologic Data) transactions")
print(result.output)

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 WONDER. 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 WONDER (Epidemiologic Data) 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 WONDER (Epidemiologic Data) MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Create an `MCPToolset` using the unified HTTP approach with your Vinkius URL, then pass it to your Agent's `toolsets` parameter.

No. That class is deprecated. You must use the `MCPToolset` wrapper to configure this MCP connection to external servers running via Streamable HTTP or SSE transports.

The framework intercepts malformed responses from the CDC API at runtime. It throws a strict validation error, preventing the agent from hallucinating data to fill in the gaps.

Yes. The framework is entirely model-agnostic. As long as your local model supports tool calling, it can format the required JSON parameters and execute the queries.

The MCP connection is handled through an isolated, zero-trust sandbox. The specific demographic variables and geographic regions you search for are wiped from memory the second the HTTP transport closes.

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