Clear the local Confluence response cache.
AI agents call cwiki_clear_cache to permanently remove resources in CwikiMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cache is a non-reversible deletion of locally stored data (cached responses). However, the blast radius is low because the cache is local and read-only (no source data is modified); the worst outcome is a performance penalty as data must be re-fetched. Still, it permanently removes the cached state, placing it in the Destructive category rather than Write.
From the tool's definition 'Clear the local Confluence response cache' — irreversibly removes cached data
Attacks that exploit this kind of access
Clear the local Confluence response cache. It is categorised as a Destructive tool in the CwikiMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cwiki MCP server in PolicyLayer and add a rule for cwiki_clear_cache: 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 CwikiMCP. Nothing to install.
cwiki_clear_cache 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 cwiki_clear_cache 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 cwiki_clear_cache. 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.
cwiki_clear_cache is provided by the Cwiki MCP server (justinmclean/cwikimcp). 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 →