Authoritative FDA drug label (Structured Product Labeling). Give a drug name (brand/generic/substance), or an exact ndc, rxcui, or SPL setId, and get the FDA-approved label split into sections: boxed warning, indications, dosage, contraindications, warnings, adverse reactions, drug interactions, ...
AI agents call medical.drug-label 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 queries and retrieves structured informational content about drug labels without side effects. It performs a lookup/fetch operation returning read-only reference data. Even though the domain is medical, the tool itself has no capability to prescribe, dispense, modify records, execute medical procedures, or cause financial transactions.
From the tool's definition Tool retrieves and returns FDA drug label data: 'get the FDA-approved label split into sections' with various informational fields. No modification, deletion, or execution capabilities described. Data source is 'free, public-domain FDA data.'
Attacks that exploit this kind of access
Authoritative FDA drug label (Structured Product Labeling). Give a drug name (brand/generic/substance), or an exact ndc, rxcui, or SPL setId, and get the FDA-approved label split into sections: boxed warning, indications, dosage, contraindications, warnings, adverse reactions, drug interactions, special populations, pregnancy, mechanism of action, ingredients — plus identity metadata and a hasBoxedWarning flag. Free, public-domain FDA data. 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-label: 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-label 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-label 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-label. 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-label 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 →