AI agents call policy_delete to permanently remove resources in AWS Serverless MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Policy deletion is a destructive operation that cannot be undone and removes access controls irreversibly. This falls squarely under the Destructive category. While severity could vary based on policy scope, the high confidence in destructive nature and potential blast radius of removing critical access policies warrants 'high' severity.
From the tool's definition Tool name 'policy_delete' indicates deletion of AWS IAM policies, which is irreversible. The empty description prevents confirmation of exact behavior, but the naming convention combined with AWS Serverless context strongly indicates policy removal.
Documented attack patterns abuse exactly the kind of access policy_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Serverless MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for policy_delete:
{
"version": "1",
"default": "deny",
"hide": [
"policy_delete"
]
}policy_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
policy_delete. It is categorised as a Destructive tool in the AWS Serverless MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS Serverless MCP Server MCP server in PolicyLayer and add a rule for policy_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 Serverless MCP Server. Nothing to install.
policy_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 policy_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 policy_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.
policy_delete is provided by the AWS Serverless MCP Server MCP server (awslabs.aws-serverless-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Serverless MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 AWS Serverless MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.