Remove items from a regular (non-smart) collection.
AI agents call remove_from_collection to permanently remove resources in Mcp Plex — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing items from a collection is a destructive operation that cannot be automatically undone. While the underlying media files are not deleted, the collection membership is lost and would require manual re-addition. This warrants a Destructive classification with medium severity since only collection associations are affected, not the media itself.
From the tool's definition 'Remove items from a regular (non-smart) collection' — removing items is an irreversible deletion of the association between media and a collection
Attacks that exploit this kind of access
Remove items from a regular (non-smart) collection. It is categorised as a Destructive tool in the Mcp Plex MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Plex MCP server in PolicyLayer and add a rule for remove_from_collection: 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 Mcp Plex. Nothing to install.
remove_from_collection 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 remove_from_collection 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 remove_from_collection. 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.
remove_from_collection is provided by the Mcp Plex MCP server (obrien-matthew/mcp-plex). 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 →