Delete a cache file
AI agents call tdarr_delete_cache_file to permanently remove resources in Tdarr — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes data (a cache file), which cannot be undone. This meets the Destructive category definition. Severity is high because deleting cache files could disrupt transcoding operations, corrupt workflow state, or cause service degradation, though it is not a direct financial or critical system impact. Confidence is high because the intent is unambiguous from both the name and description.
From the tool's definition Tool name contains 'delete' and description states 'Delete a cache file' — this is an irreversible removal of data.
Attacks that exploit this kind of access
Delete a cache file. It is categorised as a Destructive tool in the Tdarr MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tdarr MCP server in PolicyLayer and add a rule for tdarr_delete_cache_file: 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 Tdarr. Nothing to install.
tdarr_delete_cache_file 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 tdarr_delete_cache_file 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 tdarr_delete_cache_file. 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.
tdarr_delete_cache_file is provided by the Tdarr MCP server (maximeallanic/tdarr-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 →