How to Use the HHS Open Payments MCP in AutoGen

Let AutoGen agents debate healthcare compliance risks using live payment data.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel AutoGen debates with hard data

The `query_dataset` tool forces your agents to base their arguments on actual financial transactions. A compliance agent flags a doctor for high meal payments, while a sales agent queries the database to prove those payments are industry standard. They argue over the SoQL results. The multi-agent framework ensures that neither side wins until the raw data supports their conclusion. You watch the system negotiate the actual risk level using real numbers from the MCP Server.

Verify identities across agents

The `search_physicians` tool gives your researcher agent the exact NPI numbers needed to track individuals. It hands those profiles to a reviewer agent, which then runs `search_hospitals` to map out potential conflicts of interest. If the reviewer finds a mismatch, it pushes back on the researcher. The conversation loops until both agents agree they have identified the correct medical professional and their affiliated teaching institutions.

Coordinate bulk data audits

The `list_datasets` tool lets your planner agent see every available reporting year. It uses `get_dataset` to check the file sizes and metadata before assigning extraction tasks to worker agents. A dedicated worker agent then calls `download_dataset` to pull the JSON. The agents coordinate to split the parsing workload, ensuring you get a complete audit without overloading the system.

Setup guide

Set up HHS Open Payments 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 HHS Open Payments 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="HHS Open Payments_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent HHS Open Payments 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="HHS Open Payments_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent HHS Open Payments 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 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 AutoGen

Install the autogen-ext package with MCP support. Initialize the server tools with StreamableHttpServerParams and pass them to your AssistantAgent constructor.

Yes. You can give the query tools to a data-fetching agent and the dataset listing tools to a planner agent. They will coordinate their API calls during the conversation.

The agents read the server errors. If a tool call fails, the executing agent tells the group, and they negotiate a backoff strategy before trying again.

No. The McpToolAdapter converts the Open Payments parameters automatically. Your agents understand exactly what arguments the search tools require.

The server strictly processes public payment amounts and provider names. Vinkius routes the calls through a stateless execution environment, so the internal debate your agents have about a doctor's compliance risk never leaves your local machine.

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