This record as markdown: /tools/aws/set-pop.md
What set_pop does on AWS
AI agents call set_pop to permanently remove resources in AWS, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why set_pop is rated Critical
The tool irreversibly removes random member(s) from a Redis set (SPOP operation). Removal is permanent and cannot be undone without rewriting the data. Since it destructively modifies the set by deleting elements, it falls under Destructive. Severity is medium because it operates on a single key's members, but misuse (wrong key or count) could lead to unrecoverable data loss.
From the tool's definition "Remove and return random member(s) from set" - the tool permanently removes members from a set
Attacks that exploit this kind of access
The rule that runs set_pop safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AWS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For set_pop, this is the rule to start with:
set_pop is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AWS, apply this rule, and every set_pop call is checked against it from then on.
Questions about set_pop
Remove and return random member(s) from set. Args: key: The name of the key count: Number of members to pop (optional) Returns: Popped member(s) or error message. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS MCP server in PolicyLayer and add a rule for set_pop: 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. Nothing to install.
set_pop 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 set_pop 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 set_pop. 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.
set_pop is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AWS, and thousands of servers like it.
Across the catalogue