Delete snapshot by ID
AI agents call delete_snapshot to permanently remove resources in Snapshot — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes stored snapshots without the ability to undo the action. While the blast radius is limited to conversation snapshots rather than production data, deletion is irreversible and could result in loss of important saved work context. The high severity reflects the potential for an AI agent to inadvertently delete multiple snapshots, disrupting workflow continuity.
From the tool's definition Tool name 'delete_snapshot' and description 'Delete snapshot by ID' directly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete snapshot by ID. It is categorised as a Destructive tool in the Snapshot MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Snapshot MCP server in PolicyLayer and add a rule for delete_snapshot: 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 Snapshot. Nothing to install.
delete_snapshot 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_snapshot 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_snapshot. 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_snapshot is provided by the Snapshot MCP server (whenmoon-afk/snapshot-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 →