AI agents invoke stop_application to trigger actions in AWS Transform MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Stopping an application is an irreversible operational action that terminates a running process or service. This falls under Execute because it triggers external operations whose effects depend on arguments (which application to stop). While not Destructive (data is not permanently deleted), it has high blast radius if misused by an agent—unintended application shutdowns could cause service outages.
From the tool's definition Tool name 'stop_application' indicates triggering an external operation (stopping an application), which is an Execute-class action. The tool description is empty, limiting specificity.
Documented attack patterns abuse exactly the kind of access stop_application gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Transform MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_application:
{
"version": "1",
"default": "deny",
"tools": {
"stop_application": {
"limits": [
{
"counter": "stop_application_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_application stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
stop_application. It is categorised as a Execute tool in the AWS Transform MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AWS Transform MCP Server MCP server in PolicyLayer and add a rule for stop_application: 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 Transform MCP Server. Nothing to install.
stop_application is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the stop_application 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 stop_application. 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.
stop_application is provided by the AWS Transform MCP Server MCP server (awslabs.aws-transform-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Transform 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 Transform MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.