This record as markdown: /tools/aws/cache-delete.md
What cache_delete does on AWS
AI agents call cache_delete to permanently remove resources in AWS, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why cache_delete is rated Critical
The tool permanently removes cached data indexed by a key. While cache deletion is typically reversible through re-computation or re-population, the function itself performs an irreversible deletion action on stored state. In the context of an AI agent misusing this tool, it could delete critical cached values that other systems depend on, causing service degradation or data loss.
From the tool's definition Tool name 'cache_delete' and description explicitly states 'Delete a value from the cache', which is an irreversible deletion operation.
Attacks that exploit this kind of access
The rule that runs cache_delete safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AWS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cache_delete, this is the rule to start with:
cache_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AWS, apply this rule, and every cache_delete call is checked against it from then on.
Questions about cache_delete
Delete a value from the cache. Args: key: The key to delete Returns: Success message or error message. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS MCP server in PolicyLayer and add a rule for cache_delete: 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 AWS. Nothing to install.
cache_delete 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 cache_delete 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 cache_delete. 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.
cache_delete is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AWS, and thousands of servers like it.
Across the catalogue