Delete a shelf (moves to recycle bin)
AI agents call delete_shelf to permanently remove resources in BookStack MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion operations that remove data structures are destructive regardless of whether they move items to a recycle bin, as they prevent normal access to the shelf and its contents. The blast radius is high because an AI agent deleting the wrong shelf could remove significant wiki organization and content grouping.
From the tool's definition Tool name 'delete_shelf' and description 'Delete a shelf (moves to recycle bin)' indicate irreversible removal of a shelf entity, even though it goes to a recycle bin rather than permanent deletion.
Attacks that exploit this kind of access
Delete a shelf (moves to recycle bin). It is categorised as a Destructive tool in the BookStack MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the BookStack MCP Server MCP server in PolicyLayer and add a rule for delete_shelf: 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 BookStack MCP Server. Nothing to install.
delete_shelf 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 delete_shelf 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 delete_shelf. 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.
delete_shelf is provided by the BookStack MCP Server MCP server (lautarobarba/bookstack_mcp_server). 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 →