Delete an object from S3
AI agents call s3_object_delete to permanently remove resources in AWS MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes objects from S3 without recovery option (S3 does not restore deleted objects by default). Deletion is irreversible and represents the most severe category. The high severity reflects the blast radius: an AI agent error could result in unrecoverable loss of critical business data, backups, or archives stored in S3.
From the tool's definition Tool name 's3_object_delete' and description 'Delete an object from S3' explicitly indicate irreversible deletion of data from cloud storage.
Attacks that exploit this kind of access
Delete an object from S3. It is categorised as a Destructive tool in the AWS MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS MCP Server MCP server in PolicyLayer and add a rule for s3_object_delete: 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 AWS MCP Server. Nothing to install.
s3_object_delete 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 s3_object_delete 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 s3_object_delete. 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.
s3_object_delete is provided by the AWS MCP Server MCP server (rishikavikondala/mcp-server-aws). 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 →