How to Use the HHS Open Payments MCP in LangChain

Q: Can LangChain agents filter HHS Open Payments records?

Yes. Your agent uses the querydataset tool to run SoQL filters. This limits the data payload and keeps token usage low.

Build investigative AI pipelines that track healthcare money with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HHS Open Payments MCP to LangChain

Create your Vinkius account to connect HHS Open Payments 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 HHS Open Payments with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain identity checks in LangChain

The `search_physicians` tool kicks off your compliance workflow by resolving doctor identities directly from the HHS database. You feed the output into your agent, which determines if the name matches your internal records. From there, the ReAct agent decides the next step. The system might pass the physician's NPI into `query_dataset` to pull their specific financial transactions. LangSmith traces the exact token usage and latency of every API call you make to the MCP Server.

Filter transactions with SoQL

The `query_dataset` tool lets your agent execute SoQL queries against millions of payment records. You don't have to download the entire database just to find out if a specific orthopedic surgeon took a consulting fee. Your multi-agent setup evaluates the returned rows. If the transaction volume looks suspicious, the agent triggers `search_hospitals` to map out the doctor's institutional affiliations. The output becomes the input for your final risk report.

Automate bulk data retrieval

The `list_datasets` tool exposes the full catalog of available Open Payments files. Your pipeline reads the metadata using `get_dataset` to verify update timestamps before pulling any actual records. When you need the raw numbers offline, your agent calls `download_dataset` to cache the JSON. This keeps your application from hitting rate limits during intensive compliance audits.

Setup guide

Set up HHS Open Payments 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 HHS Open Payments 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({
    "hhs-open-payments-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 HHS Open Payments 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 HHS Open Payments. 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 HHS Open Payments 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 HHS Open Payments MCP in LangChain

Install the langchain-mcp-adapters and langgraph packages. Configure the MultiServerMCPClient to point at the Vinkius endpoint. Pass the retrieved tools directly to your ReAct agent.

Yes. Your agent uses the query_dataset tool to run SoQL filters. This limits the data payload and keeps token usage low.

LangGraph handles retries automatically. If a server timeout occurs while searching for a hospital, the agent falls back to previous steps or alerts the user.

It does. Every call to the Open Payments API registers as a distinct tool invocation. You see exactly what the agent asked and what the server returned.

The server processes public financial relationships and physician NPIs, not protected health information. The MCP architecture ensures your agent only reads the records you explicitly request, and Vinkius drops the ephemeral sandbox immediately after the 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