How to Use the CMS.gov Data MCP in LangChain

Feed live Medicare data and hospital ratings directly into your LangChain reasoning loops.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map provider networks using LangChain agents

`search_doctors` finds Medicare-enrolled clinicians based on specialty or location, feeding NPI numbers directly into subsequent chain links. Your LangChain agent receives these NPIs and immediately passes them to `get_doctor_by_npi` to pull exact practice addresses and enrollment statuses without manual coding. This sequential execution turns raw directory lookups into verified provider profiles. By passing output from one tool directly as the input for the next, your workflows map entire regional healthcare networks in a single run.

Track CMS datasets inside your LangChain pipelines

`list_datasets` retrieves the active identifiers and publication dates from the open data catalog of the Centers for Medicare & Medicaid Services. Your agent inspects this list, identifies updated files, and uses `get_dataset_metadata` to grab publisher information and modification timestamps. We run this server inside a secure V8 sandbox to make sure your pipeline remains isolated while processing public datasets. This setup keeps your data pipelines clean and predictable, letting you focus on building complex multi-step chains.

Audit facility quality with this MCP Server

`search_hospitals` pulls live quality ratings and emergency service availability directly into your LangSmith tracing dashboard. Your agent evaluates these hospital ratings alongside nursing home data from `search_nursing_homes` to compare regional care options. Having this MCP Server connected directly to your chain lets you trace every single tool call. You see exactly how the agent evaluates hospital stars and nursing home locations, giving you full visibility into the decision-making process.

Setup guide

Set up CMS.gov Data 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 CMS.gov Data 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({
    "cmsgov-data-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 CMS.gov Data 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 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 LangChain

You initialize the MultiServerMCPClient with our endpoint and pass the tools directly to your agent constructor. The agent can then use `search_doctors` to find providers and immediately feed those NPIs into `get_doctor_by_npi`.

Yes, every query made through this MCP Server shows up in your LangSmith dashboard. You can trace the latency and exact outputs of tools like `get_hospital_ratings` or `search_nursing_homes` within your active chain.

The agent uses a ReAct loop to decide which tools to call based on user input. For example, it might list datasets using `list_datasets` first, analyze the metadata, and then query specific provider specialties if the user asks for regional trends.

Yes, the MultiServerMCPClient handles aggregation. You can run this Medicare data server alongside other tools, allowing your agent to query hospital ratings and cross-reference them with external private databases.

We run the MCP Server in an ephemeral, zero-trust V8 sandbox that handles Medicare provider and hospital rating queries securely. No search parameters or provider NPIs are stored after your LangChain session completes.

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