Soft-delete a wiki page (reversible). The entry stops appearing in
AI agents call wiki_delete to permanently remove resources in Llama — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although the deletion is described as reversible (suggesting recovery via restore mechanisms), the tool's core purpose is to remove data from visibility and availability. Deletion operations fall under the Destructive category due to their irreversible user-facing impact, even if technical recovery is possible.
From the tool's definition Tool name is 'wiki_delete' and description states it performs a 'Soft-delete' operation on a wiki page. Despite being marked as 'reversible', the primary function is deletion of content.
Attacks that exploit this kind of access
Soft-delete a wiki page (reversible). The entry stops appearing in. It is categorised as a Destructive tool in the Llama MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Llama MCP server in PolicyLayer and add a rule for wiki_delete: 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 Llama. Nothing to install.
wiki_delete 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 wiki_delete 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 wiki_delete. 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.
wiki_delete is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →