Clean up the server: remove Jellyfin cache, temp files, orphan downloads, ghost entries in Sonarr/Radarr, and qBittorrent completed torrents. Two-step flow: dryRun=false without confirmToken returns a preview + a fresh token; show the report to the user, then re-call dryRun=false with that token ...
AI agents call cleanup_server to permanently remove resources in Mediabox MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the tool includes a two-step confirmation flow (preview then apply), the actual operations are irreversible deletions: removing cache, temporary files, orphaned entries, and completed torrents. Once executed, these deletions cannot be undone. The confirmation mechanism reduces misuse risk but does not change the fundamental destructive nature of the tool.
From the tool's definition Tool description explicitly mentions 'remove Jellyfin cache, temp files, orphan downloads, ghost entries in Sonarr/Radarr, and qBittorrent completed torrents' and 'apply' operations that delete/clean data irreversibly.
Documented attack patterns abuse exactly the kind of access cleanup_server gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mediabox MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanup_server:
{
"version": "1",
"default": "deny",
"hide": [
"cleanup_server"
]
}cleanup_server 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.
Clean up the server: remove Jellyfin cache, temp files, orphan downloads, ghost entries in Sonarr/Radarr, and qBittorrent completed torrents. Two-step flow: dryRun=false without confirmToken returns a preview + a fresh token; show the report to the user, then re-call dryRun=false with that token to apply. It is categorised as a Destructive tool in the Mediabox MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mediabox MCP server in PolicyLayer and add a rule for cleanup_server: 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 Mediabox MCP. Nothing to install.
cleanup_server 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 cleanup_server 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 cleanup_server. 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.
cleanup_server is provided by the Mediabox MCP server (juancmpdev/mediabox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mediabox MCP, 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.
30 Mediabox MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.