Leert den Cache (vollstaendig oder fuer einen spezifischen Tool-Typ).
AI agents call news_cache_clear to permanently remove resources in Pypi:news Monitor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cache is a destructive (irreversible) operation that permanently removes stored data. However, since cache data is derived/temporary and can be repopulated, the blast radius is low — worst case is performance degradation or temporary loss of cached results, not loss of primary data.
From the tool's definition Leert den Cache (vollstaendig oder fuer einen spezifischen Tool-Typ) — 'Leert' means 'clears/empties', indicating irreversible deletion of cached data
Attacks that exploit this kind of access
Leert den Cache (vollstaendig oder fuer einen spezifischen Tool-Typ). It is categorised as a Destructive tool in the Pypi:news Monitor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pypi:news Monitor MCP server in PolicyLayer and add a rule for news_cache_clear: 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 Pypi:news Monitor. Nothing to install.
news_cache_clear 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 news_cache_clear 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 news_cache_clear. 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.
news_cache_clear is provided by the Pypi:news Monitor MCP server (pypi:news-monitor-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 →