清空 AppCan 文档缓存
AI agents call clear_appcan_docs_cache to permanently remove resources in AppCan Helper MCP Server — 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, non-reversible operation that permanently removes cached documentation data. While the underlying documentation can be re-fetched, the cached data itself is permanently destroyed. Severity is medium because the blast radius is limited to cached docs (no persistent data loss, just performance impact and potential temporary unavailability).
From the tool's definition 清空 AppCan 文档缓存 (Clear AppCan documentation cache) — 'clear' and 'cache' indicate irreversible deletion of cached data
Attacks that exploit this kind of access
清空 AppCan 文档缓存. It is categorised as a Destructive tool in the AppCan Helper MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AppCan Helper MCP Server MCP server in PolicyLayer and add a rule for clear_appcan_docs_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 AppCan Helper MCP Server. Nothing to install.
clear_appcan_docs_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 clear_appcan_docs_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 clear_appcan_docs_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.
clear_appcan_docs_cache is provided by the AppCan Helper MCP Server MCP server (sandy1108/appcan-helper-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 →