How to Use the CMS.gov Data MCP in CrewAI

Q: How do I pass the CMS.gov Data MCP Server to a CrewAI agent?

Add the Vinkius URL directly to the agent's mcps list during initialization. This grants that specific agent access to tools like searchdoctors and gethospitalratings.

Q: Can I restrict which CrewAI agents can access CMS.gov Data?

Yes, use MCPServerHTTP from crewai.mcp along with a toolfilter to selectively expose tools. You can let your research agent search doctors while blocking your writing agent from accessing them.

Deploy specialized teams of CrewAI agents to analyze CMS.gov Data, audit hospitals, and verify doctors autonomously.

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 CrewAI

Create your Vinkius account to connect CMS.gov Data to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate CrewAI agents for hospital quality audits

The `search_hospitals` tool allows your agent team to pull provider IDs, facility types, and star ratings. With CrewAI, you assign one agent to search for low-performing acute care facilities while a second agent analyzes the emergency service data. These agents share memory and pass findings back and forth. The researcher agent uses `get_hospital_ratings` to pinpoint specific regions, and the analyst agent compiles a report on localized healthcare gaps.

Run autonomous doctor credentialing crews

The `search_doctors` tool scans over 2.4 million active Medicare providers to find NPI numbers and practice locations. You can configure this MCP Server inside a CrewAI pipeline where a verification agent cross-references specialty claims. The crew runs `get_doctor_by_npi` to confirm Medicare enrollment status before passing the verified file to an onboarding agent. The entire process runs sequentially without requiring your team to manually search registries.

Audit regional nursing home performance autonomously

The `search_nursing_homes` tool queries elder care facilities to get their locations and overall quality ratings. Your CrewAI crew can monitor specific states, using shared context to flag nursing homes that fall below target ratings. The supervisor agent directs worker agents to pull dataset details using `list_datasets` and `get_dataset_metadata` to verify when the underlying quality scores were last modified by the government.

Setup guide

Set up CMS.gov Data MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke CMS.gov Data tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="CMS.gov Data Analyst",
    goal="Access and analyze CMS.gov Data data via MCP.",
    backstory="Expert analyst with direct CMS.gov Data access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent CMS.gov Data transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="CMS.gov Data Analyst",
        goal="Access and analyze CMS.gov Data data via MCP.",
        backstory="Expert analyst with direct CMS.gov Data access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent CMS.gov Data transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Add the Vinkius URL directly to the agent's `mcps` list during initialization. This grants that specific agent access to tools like `search_doctors` and `get_hospital_ratings`.

Yes, use `MCPServerHTTP` from `crewai.mcp` along with a `tool_filter` to selectively expose tools. You can let your research agent search doctors while blocking your writing agent from accessing them.

CrewAI's shared memory system lets agents pass the results of tools like `get_doctor_by_npi` downstream. The next agent in the hierarchy can use that NPI context to run further evaluations.

Yes, the Vinkius hosting layer supports Streamable HTTP, SSE, and stdio transports, allowing easy integration with CrewAI's Python-based connection managers.

No search parameters or provider profiles are stored. This MCP Server processes all requests inside temporary, zero-trust V8 sandboxes that self-destruct immediately after execution.

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