Delete a bookmark permanently.
AI agents call delete_bookmark to permanently remove resources in Krill To MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a bookmark, which cannot be undone. Even though bookmarks are typically lower-stakes data compared to production systems, the permanent and irreversible nature of the action, combined with the potential for an AI agent to inadvertently delete important saved references, warrants a 'high' severity rating.
From the tool's definition The tool is explicitly described as 'Delete a bookmark permanently.' The use of 'Delete' and 'permanently' clearly indicates irreversible destruction of data.
Attacks that exploit this kind of access
Delete a bookmark permanently. It is categorised as a Destructive tool in the Krill To MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Krill To MCP Server MCP server in PolicyLayer and add a rule for delete_bookmark: 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 Krill To MCP Server. Nothing to install.
delete_bookmark 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_bookmark 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_bookmark. 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_bookmark is provided by the Krill To MCP Server MCP server (krillto/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 →