How to Use the HHS Open Payments MCP in OpenAI Agents SDK

Q: How do I connect the HHS Open Payments database to OpenAI Agents SDK?

Install the package and create an MCPServerStreamableHttp instance with your endpoint URL. Pass it via the mcpservers list in your Agent constructor. The SDK auto-discovers all six tools immediately.

Q: Can OpenAI Agents SDK run SoQL queries on HHS Open Payments?

Yes. The server exposes a querydataset tool that accepts SoQL parameters. Your agent writes the query to filter records by specific payment types or amounts before pulling the data.

Q: How does OpenAI Agents SDK handle HHS Open Payments identity resolution?

The agent uses the searchphysicians and searchhospitals tools to verify entities first. This ensures subsequent payment queries target the exact registered profile instead of guessing names.

Q: What format does the dataset download tool return?

The downloaddataset tool recommends JSON for programmatic access. Your agent receives structured data that it can parse, summarize, or pass to another specialized agent in your pipeline.

Track pharma payouts directly in your OpenAI Agents SDK pipelines with zero-configuration tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect HHS Open Payments to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate SoQL queries with your MCP Server

Your agent uses the `query_dataset` tool to pull specific financial records with SoQL syntax. You feed the OpenAI agent a physician's name, and it constructs the exact query needed to extract payment amounts from the HHS database. Because OpenAI Agents SDK supports strict guardrails, you can validate these queries before execution. Your agent pulls the raw transaction data, verifies the total sums, and logs the entire trace in your OpenAI dashboard without hallucinating numbers.

Resolve medical identities before searching

You get direct lookup access to the Open Payments registry through the `search_physicians` and `search_hospitals` tools. If a user asks about a specific doctor, the agent hits the registry to resolve the correct NPI and profile details before pulling financial records. This prevents identity mismatches in production workflows. Your system hands off the resolved identity to a specialized financial agent, which then uses `get_dataset` to pull the relevant reporting year metadata.

Automate heavy government file downloads

Managing massive government files happens through the `download_dataset` tool. Your OpenAI agent requests the raw JSON export for programmatic analysis instead of scraping slow web portals. This MCP Server integration handles the network requests while your agent focuses on parsing. You set `cacheToolsList=True` in your setup, keeping the agent fast as it repeatedly checks different reporting years via `list_datasets`.

Setup guide

Set up HHS Open Payments MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all HHS Open Payments tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives HHS Open Payments tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate HHS Open Payments tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="HHS Open Payments Agent",
            instructions="You have access to HHS Open Payments tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package and create an `MCPServerStreamableHttp` instance with your endpoint URL. Pass it via the `mcp_servers` list in your Agent constructor. The SDK auto-discovers all six tools immediately.

Yes. The server exposes a `query_dataset` tool that accepts SoQL parameters. Your agent writes the query to filter records by specific payment types or amounts before pulling the data.

The agent uses the `search_physicians` and `search_hospitals` tools to verify entities first. This ensures subsequent payment queries target the exact registered profile instead of guessing names.

The `download_dataset` tool recommends JSON for programmatic access. Your agent receives structured data that it can parse, summarize, or pass to another specialized agent in your pipeline.

No. The server only touches public financial transparency records, specifically physician and teaching hospital payment data from pharmaceutical manufacturers. Your OpenAI agent executes these queries through an ephemeral V8 Isolate Sandbox, leaving zero trace of your search parameters on our infrastructure.

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