How to Use the HHS Open Payments MCP in Google ADK

Q: How do I initialize the HHS Open Payments server in Google ADK?

You instantiate an McpToolset with your endpoint URL and pass it to the tools array of your LlmAgent. The Gemini model automatically recognizes the medical payment search functions.

Q: Can my Google ADK agent filter HHS Open Payments records before downloading?

Yes. The agent uses the querydataset tool to pass SoQL filters. This restricts the payload to specific manufacturers or payment thresholds before ingestion.

Q: Does Google ADK support querying the HHS Open Payments physician registry?

It does. The searchphysicians tool is exposed directly to the agent. It looks up exact doctor profiles to ensure your compliance reports target the correct medical professional.

Q: How do I restrict which MCP tools the agent can see?

You can use the toolnames filter when setting up the toolset. This lets you expose searchhospitals while hiding downloaddataset if you want to prevent large file transfers.

Feed massive government financial transparency datasets directly into your Google ADK agents for long-context analysis.

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 Google ADK

Create your Vinkius account to connect HHS Open Payments to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Load JSON exports directly into BigQuery

The `download_dataset` tool gives your Google ADK agent access to complete reporting year exports in JSON format. Your agent pulls the raw file and loads it straight into BigQuery for enterprise warehousing. Gemini's massive context window means you can dump thousands of payment records into a single prompt. The agent reads the entire export, cross-references it with your internal hospital data, and identifies anomalous payment spikes.

Filter transactions with your MCP Server

You execute SoQL queries with the `query_dataset` tool to filter specific transactions before they hit your agent's context. Your LLM agent writes the query to isolate payments from a specific device manufacturer to a targeted teaching hospital. This keeps your pipeline efficient. Instead of downloading gigabytes of data, your Google ADK system uses `search_hospitals` to find the exact facility, then queries only the relevant financial ties.

Verify reporting year metadata automatically

Using `list_datasets` and `get_dataset`, your Google ADK agent maps the available HHS Open Payments metadata. It checks which reporting years are published and verifies the schema before running deep searches. You configure this MCP Server using `McpToolset` with `StreamableHttpServerParameters`. The agent uses `search_physicians` to verify doctor identities against the metadata, ensuring your Vertex AI pipelines process accurate compliance data.

Setup guide

Set up HHS Open Payments MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with HHS Open Payments tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="HHS Open Payments_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HHS Open Payments tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You instantiate an `McpToolset` with your endpoint URL and pass it to the `tools` array of your `LlmAgent`. The Gemini model automatically recognizes the medical payment search functions.

Yes. The agent uses the `query_dataset` tool to pass SoQL filters. This restricts the payload to specific manufacturers or payment thresholds before ingestion.

It does. The `search_physicians` tool is exposed directly to the agent. It looks up exact doctor profiles to ensure your compliance reports target the correct medical professional.

You can use the `tool_names` filter when setting up the toolset. This lets you expose `search_hospitals` while hiding `download_dataset` if you want to prevent large file transfers.

The server processes queries for pharmaceutical payments and hospital financial relationships entirely in memory. The Vinkius zero-trust architecture destroys the execution environment the moment your Google ADK agent receives the requested records, ensuring your compliance audit trails remain strictly local.

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