How to Use the HHS Open Payments MCP in Pydantic AI

Q: How do I register the HHS Open Payments tools in Pydantic AI?

Install pydantic-ai-slimmcp and initialize an MCPToolset with your server URL. Pass this toolset to your Agent constructor to expose the payment search functions.

Q: Can Pydantic AI validate the SoQL responses from HHS Open Payments?

Yes. When your agent calls querydataset, you can enforce a Pydantic return model. If the transaction records lack required fields like payment amounts, the framework fails loudly.

Q: How does Pydantic AI handle HHS Open Payments dataset metadata?

The agent uses listdatasets and getdataset to pull reporting year details. Your predefined models ensure the agent only processes years that match your compliance audit requirements.

Q: Which transport protocol should I use for this MCP Server?

Use Streamable HTTP via the unified MCPToolset setup. The older MCPServerHTTP class is deprecated. This ensures stable connections when pulling large JSON payloads from the download tool.

Enforce strict runtime validation on government healthcare payment records with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect HHS Open Payments to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Catch malformed profiles with your MCP Server

The `search_physicians` and `search_hospitals` tools connect your Pydantic AI agent directly to the federal registry. The agent queries a doctor's name, and the server returns the structured profile data. Because Pydantic AI validates every response, you define a strict model for the physician's NPI and specialty. If the government API returns a malformed record, your pipeline throws a validation error immediately instead of passing bad data downstream.

Verify transaction amounts at runtime

Agents construct SoQL parameters using the `query_dataset` tool to extract specific financial transactions. Your agent builds the query to pull consulting fees paid to a specific teaching hospital. You wrap this MCP integration using the `MCPToolset` class. When the server returns the transaction list, your Pydantic models verify that every payment amount is a valid float and every date matches your expected format.

Audit reporting years with type safety

The `download_dataset` and `list_datasets` tools handle bulk data operations for reporting year archives. Your agent checks the available datasets, grabs the metadata via `get_dataset`, and requests the JSON export. This guarantees your compliance audits run on the exact schema you expect. It does not matter if you run Anthropic or a local model; the framework forces the LLM to respect the data types returned by the Open Payments database.

Setup guide

Set up HHS Open Payments MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "hhs-open-payments-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to HHS Open Payments tools.",
)

result = await agent.run("List recent HHS Open Payments transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize an `MCPToolset` with your server URL. Pass this toolset to your Agent constructor to expose the payment search functions.

Yes. When your agent calls `query_dataset`, you can enforce a Pydantic return model. If the transaction records lack required fields like payment amounts, the framework fails loudly.

The agent uses `list_datasets` and `get_dataset` to pull reporting year details. Your predefined models ensure the agent only processes years that match your compliance audit requirements.

Use Streamable HTTP via the unified `MCPToolset` setup. The older `MCPServerHTTP` class is deprecated. This ensures stable connections when pulling large JSON payloads from the download tool.

You are querying public financial transfers between medical device makers and doctors. Our infrastructure routes your Pydantic AI requests through an ephemeral, isolated container. No search parameters or transaction data persist after the connection closes.

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