CMS Open Payments — Sunshine Act payments from pharma/device manufacturers to US physicians or teaching hospitals (~10M records per year). Lookup by NPI, name, payer (manufacturer) name, or state. Returns recipient + payer + payment (amount, date, nature: consulting/food/travel/royalty) + associa...
AI agents call health.open-payments to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool against public healthcare transparency data (Sunshine Act). The CMS Open Payments database is intentionally published for public access and physician conflict-of-interest disclosure. Querying it poses no side effects, data modification risk, or financial risk. Severity is low because the underlying data is already public and the tool merely provides access to it.
From the tool's definition Tool returns data from publicly available CMS Open Payments database: 'Lookup by NPI, name, payer (manufacturer) name, or state. Returns recipient + payer + payment (amount, date, nature: consulting/food/travel/royalty) + associated product'.
Attacks that exploit this kind of access
CMS Open Payments — Sunshine Act payments from pharma/device manufacturers to US physicians or teaching hospitals (~10M records per year). Lookup by NPI, name, payer (manufacturer) name, or state. Returns recipient + payer + payment (amount, date, nature: consulting/food/travel/royalty) + associated product (drug/device + therapeutic area). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for health.open-payments: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
health.open-payments is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the health.open-payments rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for health.open-payments. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
health.open-payments is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →