FDA medical-device recalls — devices removed or corrected in the US market due to a possible health risk. Search by device name, recalling firm (manufacturer), recall classification (I most serious / II / III), status (Ongoing/Completed/Terminated/Pending), or state, or omit all filters for the m...
AI agents call medical.device-recall 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 retrieves and displays publicly available FDA recall information. While the subject matter (medical devices) is health-related, the tool itself only reads and filters existing public data without side effects. The ability to search and filter does not elevate it beyond Read category. No reversible modifications, code execution, destructive actions, or financial transactions occur.
From the tool's definition Tool performs searches and queries on FDA medical-device recall data with no modification capabilities. Description explicitly states it 'Search by device name' and 'Returns recall number, classification, status' — purely informational retrieval.
Attacks that exploit this kind of access
FDA medical-device recalls — devices removed or corrected in the US market due to a possible health risk. Search by device name, recalling firm (manufacturer), recall classification (I most serious / II / III), status (Ongoing/Completed/Terminated/Pending), or state, or omit all filters for the most recent recalls nationwide. Returns recall number, classification, status, product description + quantity, reason, code/lot info, recalling firm + location, distribution pattern, voluntary-vs-mandated, and recall/classification/report dates, newest first. Free, public-domain FDA data. Distinct from medical.device-510k (clearances) and medical.device-event (adverse-event reports). 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.device-recall: 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.device-recall 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.device-recall 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.device-recall. 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.device-recall 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 →