How to Use the CMS.gov Data MCP in Pydantic AI

Q: How does Pydantic AI validate CMS.gov Data responses?

The MCPToolset automatically maps the server output to your Pydantic models. Any deviation from the schema triggers an immediate validation error.

Q: Can I use Pydantic AI to search CMS.gov Data by specialty?

Yes. Use the searchprovidersbyspecialty tool. Your agent receives a validated list of providers matching your criteria.

Q: Does Pydantic AI require specific CMS.gov Data configuration?

You just need the server URL for the MCPToolset. The framework handles the rest, ensuring all tool calls are typed and validated.

Strictly typed healthcare agents using Pydantic AI. Connect to CMS.gov Data with runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CMS.gov Data MCP to Pydantic AI

Create your Vinkius account to connect CMS.gov 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 CMS.gov Data with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate CMS.gov Data in Pydantic AI

Every response from `get_dataset_metadata` is checked against your Pydantic schemas. If the Medicare API returns a malformed record, your agent stops before causing a downstream error. This ensures your healthcare logic is built on solid data. You define the types, and the MCP Server fills them accurately.

Search Medicare Providers with Pydantic AI

Use `search_doctors` to find clinicians and verify their NPI enrollment status. Pydantic AI forces the model to respect the structure of the data returned by this MCP Server. You avoid the common pitfalls of LLM hallucination by enforcing a strict schema. The agent only acts on data that matches your defined requirements.

Query Hospital Quality via Pydantic AI

Call `get_hospital_ratings` to bring government quality metrics into your agent's decision tree. The results are parsed immediately into your Python objects. This approach gives you total confidence in the data. You don't have to worry about silent failures or unexpected field types when querying the CMS catalog.

Setup guide

Set up CMS.gov 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": {
        "cmsgov-data-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent CMS.gov 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 CMS.gov Data. 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 CMS.gov 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 CMS.gov Data MCP in Pydantic AI

The `MCPToolset` automatically maps the server output to your Pydantic models. Any deviation from the schema triggers an immediate validation error.

Yes. Use the `search_providers_by_specialty` tool. Your agent receives a validated list of providers matching your criteria.

You just need the server URL for the `MCPToolset`. The framework handles the rest, ensuring all tool calls are typed and validated.

The server is hosted on Vinkius and accessed via SSE or HTTP. Your agent maintains a clean state by validating every single interaction at runtime.

Only public provider and hospital data is accessible. The Vinkius infrastructure enforces strict isolation, ensuring your agent only touches the intended data types.

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