remove_library_item
AI agents call remove_library_item to permanently remove resources in Metis Public Health — 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 user's indexed PDF library. Once a library item is removed, it cannot be recovered (unless separately backed up). This is irreversible data destruction affecting the user's research knowledge base.
From the tool's definition Tool name is 'remove_library_item' — the verb 'remove' combined with 'library_item' indicates deletion of indexed PDF library content. No description provided.
Attacks that exploit this kind of access
remove_library_item. It is categorised as a Destructive tool in the Metis Public Health MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for remove_library_item: 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 Metis Public Health. Nothing to install.
remove_library_item 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_library_item 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_library_item. 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_library_item is provided by the Metis Public Health MCP server (sveritg/metis_ph). 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 →