Forget a torrent, keeping the files.
AI agents call forget_torrent to permanently remove resources in rqbit Torrent Client MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Forgetting a torrent removes it from the client permanently with no indication of an undo mechanism. While the files are preserved, the torrent metadata, state, and management context are irreversibly lost from the client. This is analogous to a delete operation on the torrent record, making it Destructive.
From the tool's definition 'Forget a torrent, keeping the files' — removes the torrent from the client's tracking/management irreversibly
Attacks that exploit this kind of access
Forget a torrent, keeping the files. It is categorised as a Destructive tool in the rqbit Torrent Client MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the rqbit Torrent Client MCP server in PolicyLayer and add a rule for forget_torrent: 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 rqbit Torrent Client MCP. Nothing to install.
forget_torrent 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 forget_torrent 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 forget_torrent. 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.
forget_torrent is provided by the rqbit Torrent Client MCP server (philogicae/rqbit-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 →