How to Use the CMS.gov Data MCP in AutoGen

Q: How do I register CMS.gov Data tools with AutoGen agents?

You import mcpservertools from autogen-extmcp and pass our server URL. This exposes tools like searchdoctors directly to your AssistantAgent constructor.

Let your AutoGen agents debate and analyze Medicare provider networks and hospital quality.

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 AutoGen

Create your Vinkius account to connect CMS.gov Data 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 CMS.gov Data with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run collaborative medical audits using AutoGen

`search_hospitals` retrieves quality ratings, facility types, and emergency service availability for any US location. In your AutoGen setup, a research agent pulls this data while an analyst agent evaluates the quality metrics to find the best local care options. This multi-agent debate ensures that hospital ratings are thoroughly scrutinized before making a final recommendation. The agents check each other's work, comparing hospital data with nursing home metrics from `search_nursing_homes`.

Validate provider enrollment with this MCP Server

`get_doctor_by_npi` pulls a clinician's complete Medicare enrollment profile and practice details using their 10-digit NPI. Your AutoGen security agent can request this data to verify a provider's active status. Meanwhile, a coordinator agent uses `search_providers_by_specialty` to find matching doctors in the area. The MCP Server handles the connection, letting your agents collaborate to build a verified list of active, enrolled specialists without human intervention.

Analyze CMS datasets through multi-agent consensus

`list_datasets` exposes the entire open data catalog from the Centers for Medicare & Medicaid Services. Your AutoGen agents can debate which datasets are most relevant to your current project. One agent uses `get_dataset_metadata` to verify publication dates, while another checks the dataset size and description. They reach a consensus on which data source to prioritize, ensuring your pipeline uses the most reliable information.

Setup guide

Set up CMS.gov Data 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 CMS.gov Data 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="CMS.gov Data_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CMS.gov Data 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="CMS.gov Data_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CMS.gov Data 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 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 AutoGen

You import `mcp_server_tools` from `autogen-ext[mcp]` and pass our server URL. This exposes tools like `search_doctors` directly to your AssistantAgent constructor.

Yes, your agents can coordinate tool usage. One agent can call `search_hospitals` to find facilities, while another uses `get_hospital_ratings` to analyze the quality metrics in parallel.

The McpToolAdapter automatically translates the CMS schemas into the format AutoGen expects. This means your agents can immediately query provider NPIs and hospital ratings without manual schema mapping.

It uses the Streamable HTTP transport, which provides a fast connection to our hosted V8 sandbox. This allows your agents to query massive directories like `search_providers_by_specialty` with minimal latency.

Yes, all interactions through this MCP Server are executed in a zero-trust, ephemeral sandbox. We manage the secure connection token, and your search parameters are wiped as soon as your AutoGen session ends.

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