AI agents call delete_app to permanently remove resources in AWS Bedrock AgentCore MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'delete_app' strongly suggests permanent removal of an application, which is an irreversible destructive operation. Without a description, confidence is moderately reduced, but the deletion semantics are clear enough to categorize as Destructive rather than Execute. The critical severity reflects the potential blast radius of accidentally deleting entire applications in an AWS environment.
From the tool's definition Tool name 'delete_app' indicates irreversible deletion of an application resource. No description provided to clarify scope or reversibility.
Documented attack patterns abuse exactly the kind of access delete_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Bedrock AgentCore MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_app:
{
"version": "1",
"default": "deny",
"hide": [
"delete_app"
]
} delete_app 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.
delete_app. It is categorised as a Destructive tool in the AWS Bedrock AgentCore MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS Bedrock AgentCore MCP Server MCP server in PolicyLayer and add a rule for delete_app: 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 Bedrock AgentCore MCP Server. Nothing to install.
delete_app 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 delete_app 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 delete_app. 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.
delete_app is provided by the AWS Bedrock AgentCore MCP Server MCP server (awslabs.amazon-bedrock-agentcore-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Bedrock AgentCore 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 Bedrock AgentCore MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.