Delete an object from S3.
AI agents call s3_delete_object to permanently remove resources in Integrations MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data from Amazon S3 storage. Once deleted, the object cannot be recovered unless S3 versioning or backup systems are in place. The destructive nature of deletion operations places this in the Destructive category rather than Write. High severity reflects the permanent data loss risk if an AI agent misuses this tool on critical objects.
From the tool's definition Tool name is 's3_delete_object' and description states 'Delete an object from S3.' The verb 'delete' is explicitly destructive, and S3 object deletion is irreversible without backups or versioning.
Attacks that exploit this kind of access
Delete an object from S3. It is categorised as a Destructive tool in the Integrations MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Integrations MCP server in PolicyLayer and add a rule for s3_delete_object: 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 Integrations MCP. Nothing to install.
s3_delete_object 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_delete_object 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_delete_object. 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_delete_object is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →