identity_delete_resource_policy
AI agents call identity_delete_resource_policy to permanently remove resources in AWS Labs postgres MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Delete operations that remove access control policies are destructive because they cannot be undone and directly impact system security and authorization. Even though the description is empty (lowering confidence slightly), the explicit 'delete' in the name combined with the 'identity' context (AWS IAM) makes this clearly destructive rather than write.
From the tool's definition Tool name 'identity_delete_resource_policy' contains the verb 'delete', indicating irreversible removal of a resource policy. The AWS identity context suggests this affects IAM/access control policies.
Documented attack patterns abuse exactly the kind of access identity_delete_resource_policy gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Labs postgres MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for identity_delete_resource_policy:
{
"version": "1",
"default": "deny",
"hide": [
"identity_delete_resource_policy"
]
}identity_delete_resource_policy 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.
identity_delete_resource_policy. It is categorised as a Destructive tool in the AWS Labs postgres MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS Labs postgres MCP Server MCP server in PolicyLayer and add a rule for identity_delete_resource_policy: 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 Labs postgres MCP Server. Nothing to install.
identity_delete_resource_policy 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 identity_delete_resource_policy 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 identity_delete_resource_policy. 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.
identity_delete_resource_policy is provided by the AWS Labs postgres MCP Server MCP server (awslabs.postgres-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Labs postgres 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 Labs postgres MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.