• FILTERED
  • AGGREGATED
  • VERIFIED
  • HUMAN

How to filter healthcare spending data with your AI

Connect the HHS Open Payments MCP to your AI client once. From there, you can query the entire database using natural language.

Ask AI about this page

Short answer

How can I filter HHS Open Payments data with my AI?

Your AI uses SoQL queries to pull specific records from the HHS datasets. You can isolate payments by company, state, or dollar amount to get the exact subset you need. Here is how the process works.

Data outcomes

Where your data lands.

What you get after your AI runs a query.

FILTERED

Targeted payment lists

The AI uses query tools to strip away irrelevant records. You get a clean list of payments that match your specific criteria.

AGGREGATED

Spending summaries

Your agent can group data to show total spend per company or per state. This turns raw rows into usable totals.

VERIFIED

Dataset snapshots

The AI identifies which specific datasets are available for your search. You'll know exactly which version of the records you are looking at.

HUMAN

Manual audit

You review the final filtered results. The AI handles the heavy lifting of the query, but you make the final call on the data's relevance.

The workflow

What your AI does when the data arrives.

The AI moves from exploring the available data to executing precise filters.

  1. Locate datasets

    The AI checks the HHS Open Payments repository to find the specific tables containing the spending information you want.

    list_datasets

  2. Build SoQL queries

    Your agent translates your plain English request into a structured SoQL command to target specific columns and rows.

    query_dataset

  3. Isolate records

    The AI executes the query to pull only the records that meet your state, amount, or company constraints.

    query_dataset

  4. Format results

    The agent organizes the returned payment data into a readable format for your review.

    query_dataset

Try it

Copy these to start.

Use these prompts to begin your analysis.

Starting points

Swap out the bracketed terms for the specific company or state you are investigating.

HHS Open Payments Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_7u23vXwhxnAQUVTHtJVGNkWOGXYiG0Rpr2DQtEqC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — HHS Open Payments capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "hhs-open-payments-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_7u23vXwhxnAQUVTHtJVGNkWOGXYiG0Rpr2DQtEqC/mcp"
    }
  }
}
Copy into chat04

  • List all available datasets in the HHS Open Payments connector.

  • Find all payment records in California where the amount is greater than $10,000.

  • Show me the total payments made to [Company Name] in the last year.

  • Query the dataset for all payments made to physicians in [State Name].

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect HHS Open Payments once, then ask.

One click connects the MCP to your client. Your credentials stay encrypted and the setup is handled on our end.

Connect HHS Open Payments to your AI

FAQ

How this task behaves

  • 01

    Can the AI update or delete payment records?

    No. The tools only allow the AI to list and query existing datasets. It cannot modify the HHS data.

  • 02

    Can I use this to find specific doctor names?

    Yes, as long as that information is contained within the available HHS Open Payments datasets.

  • 03

    Does the AI write the SoQL queries itself?

    Yes. You provide the intent in plain English, and the AI generates and runs the necessary query commands.

  • 04

    Can the AI export this data to a CSV file?

    No. The AI can only retrieve and display the data within your chat interface.

  • 05

    How does the AI know which dataset to use?

    It first uses the list tool to see what is available, then selects the appropriate dataset to run your query against.

  • More questions about HHS Open Payments? The Connector page answers them. See everything the HHS Open Payments Connector can do

Connect HHS Open Payments to Claude, Cursor, ChatGPT & more