Remove specific rule.
AI agents call delete_rule to permanently remove resources in Starlog — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on project rules stored within a documentation workflow system. Even though the scope is limited to rule records rather than critical project data, the action is permanent and cannot be reversed. An AI agent that mistakenly deletes important project governance rules could disrupt team workflows and require manual recovery.
From the tool's definition Tool name is 'delete_rule' and description states 'Remove specific rule' — this irreversibly deletes data (project rules) that cannot be undone.
Attacks that exploit this kind of access
Remove specific rule. It is categorised as a Destructive tool in the Starlog MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Starlog MCP server in PolicyLayer and add a rule for delete_rule: 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 Starlog. Nothing to install.
delete_rule 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_rule 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_rule. 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_rule is provided by the Starlog MCP server (sancovp/starlog-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 →