AI agents call gov.fda-device-events 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 publicly available regulatory data from the FDA's MAUDE database. It has no side effects—it does not create, modify, delete, execute code, or commit financial transactions. Even if an AI agent misuses it by querying extensively, the worst outcome is information disclosure of already-public data, which poses minimal harm. The tool is clearly Read-category.
From the tool's definition Tool retrieves 'FDA medical device adverse event reports (MAUDE)' and supports filtering by device, manufacturer, or product code.
Attacks that exploit this kind of access
FDA medical device adverse event reports (MAUDE), newest first. Filter by device, manufacturer, or product code. 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 gov.fda-device-events: 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.
gov.fda-device-events 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 gov.fda-device-events 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 gov.fda-device-events. 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.
gov.fda-device-events 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 →