Classify a medical device across global regulatory jurisdictions. Returns risk classification, regulatory pathway, estimated timeline, and costs for each target market. Supports 15 jurisdictions: US (FDA), EU (MDR), SG (HSA), AU (TGA), JP (PMDA), CN (NMPA), CA (Health Canada), KR (MFDS), IN (CDSC...
AI agents call classify_device to retrieve information from Regmd without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a data retrieval and classification operation against regulatory databases. It has no side effects on systems or data—it does not create, modify, delete, or execute external operations. The output is informational guidance for medical device regulatory compliance planning.
From the tool's definition The tool 'classify_device' returns information ('risk classification, regulatory pathway, estimated timeline, and costs') without modifying, creating, deleting, or executing operations.
Attacks that exploit this kind of access
Classify a medical device across global regulatory jurisdictions. Returns risk classification, regulatory pathway, estimated timeline, and costs for each target market. Supports 15 jurisdictions: US (FDA), EU (MDR), SG (HSA), AU (TGA), JP (PMDA), CN (NMPA), CA (Health Canada), KR (MFDS), IN (CDSCO), BR (ANVISA), TH (Thai FDA), MY (MDA), VN (VMOH), PH (FDA Philippines), HK (MDCO). Use ISO country codes or agency abbreviations for targetMarkets. It is categorised as a Read tool in the Regmd MCP Server, which means it retrieves data without modifying state.
Register the Regmd MCP server in PolicyLayer and add a rule for classify_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 Regmd. Nothing to install.
classify_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 classify_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 classify_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.
classify_device is provided by the Regmd MCP server (zubi-wiz/regmd-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 →