FDA drug approval history from Drugs@FDA. Give a drug name (brand/generic), an FDA application number (e.g. NDA019872), or a sponsor, and get each approved application with its products (brand, active ingredients + strengths, dosage form, route, marketing status, TE code) and full submission hist...
AI agents call medical.drug-approval 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 only reads and returns historical FDA drug approval records. It does not create, modify, delete, or execute code. There are no side effects, no financial transactions, and no irreversible actions. The blast radius of misuse is minimal—an agent could retrieve approval records it shouldn't, but cannot alter FDA data or trigger external operations.
From the tool's definition The tool retrieves and queries publicly available FDA drug approval history data. Operations described are: 'give a drug name...and get each approved application', 'submission history', 'approvals/supplements + dates'.
Attacks that exploit this kind of access
FDA drug approval history from Drugs@FDA. Give a drug name (brand/generic), an FDA application number (e.g. NDA019872), or a sponsor, and get each approved application with its products (brand, active ingredients + strengths, dosage form, route, marketing status, TE code) and full submission history (approvals/supplements + dates, review priority). 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-approval: 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-approval 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-approval 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-approval. 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-approval 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 →