Deletes a backup.
AI agents call delete_backup to permanently remove resources in Observability — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on backup data. Even though it targets a backup (not the primary data source), deleting backups removes recovery options and cannot be undone. This is a destructive action with potentially high blast radius if an AI agent misuses it, as it could permanently eliminate disaster recovery capabilities.
From the tool's definition Tool name 'delete_backup' with description 'Deletes a backup' indicates irreversible deletion of backup data.
Attacks that exploit this kind of access
Deletes a backup. It is categorised as a Destructive tool in the Observability MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Observability MCP server in PolicyLayer and add a rule for delete_backup: 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 Observability. Nothing to install.
delete_backup 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_backup 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_backup. 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_backup is provided by the Observability MCP server (@google-cloud/observability-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 →