delete_runbook
AI agents call delete_runbook to permanently remove resources in Runbook — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool is named delete_runbook, which signals permanent removal of runbook resources. Deletion cannot be undone and represents data loss. Without a description to clarify safeguards or scope limitations, we conservatively classify this as Destructive rather than Write. The high severity reflects that runbooks could contain critical automation logic, so loss of a runbook could disrupt operations.
From the tool's definition Tool name is 'delete_runbook' with an empty description. The verb 'delete' combined with the resource 'runbook' indicates irreversible removal of data.
Attacks that exploit this kind of access
delete_runbook. It is categorised as a Destructive tool in the Runbook MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Runbook MCP server in PolicyLayer and add a rule for delete_runbook: 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 Runbook. Nothing to install.
delete_runbook 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_runbook 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_runbook. 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_runbook is provided by the Runbook MCP server (runbookai/runbook-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 →