Permanently deletes a knowledge library.
AI agents call delete_knowledge_library to permanently remove resources in Ai Books — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data without the possibility of recovery or undo. Permanent deletion is the defining characteristic of the Destructive category. Severity is high because loss of a knowledge library could impact multiple workflows and stored context, though it is scoped to a single library rather than system-wide data, preventing a critical rating.
From the tool's definition Tool name 'delete_knowledge_library' and description 'Permanently deletes a knowledge library.' explicitly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Permanently deletes a knowledge library. It is categorised as a Destructive tool in the Ai Books MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ai Books MCP server in PolicyLayer and add a rule for delete_knowledge_library: 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 Ai Books. Nothing to install.
delete_knowledge_library 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_knowledge_library 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_knowledge_library. 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_knowledge_library is provided by the Ai Books MCP server (nvmtoxic/ai-books-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 →