Prune completed/done backlog items - remove old archived items from COMPLETED_Backlog
AI agents call prune to permanently remove resources in MCP Backlog Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes backlog items, an operation that cannot be undone. Even though the items are archived/completed, deletion is irreversible and represents data loss. The most severe category applies: Destructive > Execute > Write > Read. High severity reflects that an agent could lose important historical records or audit trails by removing archived items unexpectedly.
From the tool's definition Tool description states 'remove old archived items from COMPLETED_Backlog' - the verb 'remove' combined with 'prune' indicates irreversible deletion of data records.
Attacks that exploit this kind of access
Prune completed/done backlog items - remove old archived items from COMPLETED_Backlog. It is categorised as a Destructive tool in the MCP Backlog Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Backlog Server MCP server in PolicyLayer and add a rule for prune: 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 MCP Backlog Server. Nothing to install.
prune 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 prune 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 prune. 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.
prune is provided by the MCP Backlog Server MCP server (rwese/mcp-backlog). 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 →