清除已保存的 Cookie
AI agents call clear_saved_cookies to permanently remove resources in YST KPI Daily Report Collector — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes persisted session cookies. Once cleared, the saved authentication state is permanently removed and cannot be recovered, requiring re-authentication. This is a destructive operation with a moderate blast radius since it would break automated report collection until re-login, but does not affect external systems or user data.
From the tool's definition 清除已保存的 Cookie (Clear saved cookies)
Attacks that exploit this kind of access
清除已保存的 Cookie. It is categorised as a Destructive tool in the YST KPI Daily Report Collector MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the YST KPI Daily Report Collector MCP server in PolicyLayer and add a rule for clear_saved_cookies: 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 YST KPI Daily Report Collector. Nothing to install.
clear_saved_cookies is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_saved_cookies 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 clear_saved_cookies. 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.
clear_saved_cookies is provided by the YST KPI Daily Report Collector MCP server (xuzan9396/yst_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 →