Permanently delete an entity. Requires
AI agents call kanka_delete_entity to permanently remove resources in Kanka — 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 possibility of recovery or undo. While not financial in nature, the irreversible deletion of campaign entities (one of 18 entity types) in a world-building platform represents a destructive action with significant blast radius if triggered inappropriately by an AI agent.
From the tool's definition Tool name 'kanka_delete_entity' combined with description 'Permanently delete an entity' explicitly indicates irreversible deletion of data.
Attacks that exploit this kind of access
Permanently delete an entity. Requires. It is categorised as a Destructive tool in the Kanka MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Kanka MCP server in PolicyLayer and add a rule for kanka_delete_entity: 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 Kanka. Nothing to install.
kanka_delete_entity 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 kanka_delete_entity 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 kanka_delete_entity. 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.
kanka_delete_entity is provided by the Kanka MCP server (torinvdb/kanka-mcp). 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 →