清除图片理解缓存（手动触发）
AI agents call clear_vision_cache to permanently remove resources in MiniMax 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, irreversible operation — once the cached image-understanding results are purged, they cannot be recovered without re-processing. The blast radius is medium: misuse would force re-computation and potentially consume quota, but no permanent user data or financial assets are destroyed.
From the tool's definition 清除图片理解缓存（手动触发）— 'clear' (清除) indicates irreversible deletion of cached data
Attacks that exploit this kind of access
清除图片理解缓存（手动触发）. It is categorised as a Destructive tool in the MiniMax MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MiniMax MCP Server MCP server in PolicyLayer and add a rule for clear_vision_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 MiniMax MCP Server. Nothing to install.
clear_vision_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_vision_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_vision_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_vision_cache is provided by the MiniMax MCP Server MCP server (longhz/minimax-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 →