AI agents call get_agency_deficiency_guidance to retrieve information from Regsub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a knowledge base of regulatory guidance on common submission deficiencies. It retrieves reference information to inform regulatory strategy, similar to a lookup or search. No data is created, modified, deleted, or executed; the tool provides read-only intelligence to support compliance planning.
From the tool's definition Tool name contains 'get' and description states 'Retrieve common deficiency areas' — both indicate read-only data retrieval with no modification or execution of external operations.
Attacks that exploit this kind of access
Retrieve common deficiency areas for FDA or EMA submissions by domain (CMC, Clinical, Labelling, Pharmacovigilance). It is categorised as a Read tool in the Regsub MCP Server, which means it retrieves data without modifying state.
Register the Regsub MCP server in PolicyLayer and add a rule for get_agency_deficiency_guidance: 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 Regsub. Nothing to install.
get_agency_deficiency_guidance 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 get_agency_deficiency_guidance 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 get_agency_deficiency_guidance. 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.
get_agency_deficiency_guidance is provided by the Regsub MCP server (pubspro/regsub-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 →