AI agents call evaluate_medical_device to retrieve information from OpenFDA FastMCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes data from FDA medical device clearances and related public health datasets. The verb 'evaluate' in context of a profile means to assess or analyze existing information, not to modify or execute external actions.
From the tool's definition Tool name 'evaluate_medical_device' and description 'Evaluate Medical Device Profile' indicate querying/analyzing existing FDA medical device data. The sibling tools all use 'search_' patterns and are explicitly for querying public health datasets.
Documented attack patterns abuse exactly the kind of access evaluate_medical_device gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenFDA FastMCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_medical_device:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_medical_device": {}
}
}evaluate_medical_device is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Evaluate Medical Device Profile. It is categorised as a Read tool in the OpenFDA FastMCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenFDA FastMCP Server MCP server in PolicyLayer and add a rule for evaluate_medical_device: 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 OpenFDA FastMCP Server. Nothing to install.
evaluate_medical_device 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 evaluate_medical_device 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 evaluate_medical_device. 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.
evaluate_medical_device is provided by the OpenFDA FastMCP Server MCP server (suyashekhande/openfda-semantic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenFDA FastMCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 OpenFDA FastMCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.