AI agents call medical.drug-price 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 tool performs a data retrieval operation against a public CMS database. It has no capability to modify, delete, or create data, and does not execute code or trigger external operations. The financial context (drug pricing) is incidental to the read-only nature of the query. No irreversible side effects are possible from calling this tool.
From the tool's definition Tool retrieves US drug pricing data from CMS NADAC without modification capabilities. Description indicates it queries and returns pricing information based on NDC codes or drug names.
Attacks that exploit this kind of access
US drug pricing from CMS NADAC (National Average Drug Acquisition Cost), the benchmark per-unit acquisition cost CMS surveys weekly. Pass ndc (11-digit NDC) for an exact product or name (e.g. 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 medical.drug-price: 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.
medical.drug-price 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 medical.drug-price 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 medical.drug-price. 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.
medical.drug-price 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 →