forget_snapshots
AI agents call forget_snapshots 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.
In restic, the 'forget' command removes snapshots from the repository. This is a destructive, irreversible operation — once a snapshot is forgotten (especially with pruning), the backup data cannot be recovered. The tool name clearly maps to restic's 'forget' subcommand. Description is empty, so confidence is slightly reduced, but the name and server context strongly indicate destructive behavior.
From the tool's definition Tool name 'forget_snapshots' combined with server context mentioning 'applying retention policies' — in restic, 'forget' removes snapshot metadata (and with --prune, associated data), which is irreversible
Attacks that exploit this kind of access
forget_snapshots. 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 forget_snapshots: 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.
forget_snapshots 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 forget_snapshots 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 forget_snapshots. 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.
forget_snapshots 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 →