Remove unreferenced data from the repository to reclaim space.
AI agents call prune_repo to permanently remove resources in Restic — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
prune_repo permanently removes data from the restic repository to reclaim space. While the data being removed is technically 'unreferenced' (orphaned), the operation itself is irreversible and destructive in nature. If an AI agent misuses this tool or miscalculates which snapshots are truly safe to prune, it could result in permanent loss of backup data.
From the tool's definition 'Remove unreferenced data from the repository' — this operation irreversibly deletes data from the backup repository. Pruning is a destructive maintenance operation that cannot be undone.
Attacks that exploit this kind of access
Remove unreferenced data from the repository to reclaim space. It is categorised as a Destructive tool in the Restic MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Restic MCP server in PolicyLayer and add a rule for prune_repo: 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 Restic. Nothing to install.
prune_repo 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_repo 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_repo. 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_repo is provided by the Restic MCP server (mohsenil85/restic-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 →