Check if a product contains known irritants for sensitive skin
AI agents call check_red_flags to retrieve information from Skincare MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a lookup/query function that retrieves and analyzes existing ingredient data to identify matches against a known irritants database. It has no side effects, does not modify data, and does not execute code or external commands.
From the tool's definition Tool description states it 'checks if a product contains known irritants' — a query operation that scans ingredient lists and returns information about potential sensitivities. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Check if a product contains known irritants for sensitive skin. It is categorised as a Read tool in the Skincare MCP MCP Server, which means it retrieves data without modifying state.
Register the Skincare MCP server in PolicyLayer and add a rule for check_red_flags: 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 Skincare MCP. Nothing to install.
check_red_flags 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 check_red_flags 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 check_red_flags. 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.
check_red_flags is provided by the Skincare MCP server (pserein/skincare-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 →