Delete a content cache.
AI agents call gemini_delete_cache_tool to permanently remove resources in MCP Gemini — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on cached content. Deletion cannot be undone, making it destructive rather than merely write-level. The high severity reflects the risk that an AI agent could permanently remove important cached data, such as compiled results, processed documents, or memoized computation results that the system depends on.
From the tool's definition Tool name contains 'delete' and description states 'Delete a content cache.' The verb 'delete' is explicitly destructive and irreversible.
Attacks that exploit this kind of access
Delete a content cache. It is categorised as a Destructive tool in the MCP Gemini MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Gemini MCP server in PolicyLayer and add a rule for gemini_delete_cache_tool: 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 MCP Gemini. Nothing to install.
gemini_delete_cache_tool 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 gemini_delete_cache_tool 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 gemini_delete_cache_tool. 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.
gemini_delete_cache_tool is provided by the MCP Gemini MCP server (mcp-gemini-crunchtools). 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 →