Manage S3 buckets: list, browse objects, check size, create, delete.
AI agents call aws_s3 to permanently remove resources in RedisNexus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Although this tool performs multiple operations (list, browse, check size, create), the ability to delete S3 buckets makes it Destructive rather than Write. S3 bucket deletion is an irreversible action that could result in permanent loss of significant data and business continuity impact. This is classified as critical severity due to the potential blast radius of data loss in a production environment.
From the tool's definition Tool description explicitly states it can 'delete' S3 buckets. Deletion of S3 buckets is irreversible and destroys data at scale.
Attacks that exploit this kind of access
Manage S3 buckets: list, browse objects, check size, create, delete. It is categorised as a Destructive tool in the RedisNexus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RedisNexus MCP server in PolicyLayer and add a rule for aws_s3: 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 RedisNexus. Nothing to install.
aws_s3 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 aws_s3 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 aws_s3. 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.
aws_s3 is provided by the RedisNexus MCP server (rajkumar-madhu/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 →