AI agents call cache_delete to permanently remove resources in Document Loader MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on cached data. While the blast radius may be limited to cache layers (not primary data), cache deletion is destructive and cannot be undone. This warrants the Destructive category and high severity, as an agent deleting cached values could disrupt application functionality, cause stale data to persist, or interfere with performance optimization.
From the tool's definition The tool is named 'cache_delete' with description 'Delete a value from the cache.' The verb 'delete' indicates irreversible removal of cached data.
Documented attack patterns abuse exactly the kind of access cache_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Document Loader MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_delete:
{
"version": "1",
"default": "deny",
"hide": [
"cache_delete"
]
}cache_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a value from the cache. It is categorised as a Destructive tool in the Document Loader MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Document Loader MCP Server 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 Document Loader MCP Server. 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 Document Loader MCP Server MCP server (awslabs.document-loader-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Document Loader MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 Document Loader MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.