Medicare utilization + payments by provider (CMS annual dataset): beneficiary counts, total services, submitted charges, Medicare payment amounts per NPI. By npi, or lastName + state. Pairs with health.open-payments.
AI agents call health.medicare-provider 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.
The tool performs data retrieval and querying of historical Medicare payment information. It is a read-only query against public CMS datasets with no side effects, no ability to modify records, and no financial transactions. The data returned is informational aggregate statistics. Confidence is high because the description clearly indicates query/retrieval semantics ('utilization + payments...
From the tool's definition Tool retrieves Medicare utilization and payment data (beneficiary counts, services, charges, payments) by querying CMS datasets using NPI or provider name/state. No modification, deletion, or financial transaction capability described.
Attacks that exploit this kind of access
Medicare utilization + payments by provider (CMS annual dataset): beneficiary counts, total services, submitted charges, Medicare payment amounts per NPI. By npi, or lastName + state. Pairs with health.open-payments. 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.medicare-provider: 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.medicare-provider 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.medicare-provider 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.medicare-provider. 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.medicare-provider 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 →