arch_delete
AI agents call arch_delete to permanently remove resources in Paparats — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name explicitly contains 'delete', which strongly implies irreversible removal of data. In the context of a code search and architecture documentation server, deletion of architectural components, decisions, lessons, or project records cannot be undone and would result in loss of valuable documentation. This falls clearly into the Destructive category rather than Write (which is reversible).
From the tool's definition Tool name 'arch_delete' with 'delete' in the name indicates irreversible deletion. Absence of description limits certainty.
Attacks that exploit this kind of access
arch_delete. It is categorised as a Destructive tool in the Paparats MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Paparats MCP server in PolicyLayer and add a rule for arch_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 Paparats. Nothing to install.
arch_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 arch_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 arch_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.
arch_delete is provided by the Paparats MCP server (@paparats/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 →