Deletes multiple objects from an S3 bucket.
AI agents call delete_objects to permanently remove resources in S3 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes data from cloud storage without reversibility. Misuse by an AI agent could lead to catastrophic data loss of potentially critical business assets, backups, or user data stored in S3. This warrants critical severity due to the scope (multiple objects), permanence, and potential business impact.
From the tool's definition Tool name 'delete_objects' and description 'Deletes multiple objects from an S3 bucket' indicate irreversible deletion of data. This is a destructive operation that cannot be undone.
Attacks that exploit this kind of access
Deletes multiple objects from an S3 bucket. It is categorised as a Destructive tool in the S3 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the S3 MCP server in PolicyLayer and add a rule for delete_objects: 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 S3. Nothing to install.
delete_objects 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_objects 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_objects. 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_objects is provided by the S3 MCP server (konmam/s3-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 →