AI agents invoke stop_scan to trigger actions in AWS. 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 a security scan is an operational action that interrupts a running process, which qualifies as Execute rather than Read. However, it is not destructive (doesn't delete data), not financial, and not a simple write operation.
From the tool's definition Tool name 'stop_scan' and description 'Stop a running security scan' indicate an action that halts an ongoing operation. This is an executable action that triggers an external effect (terminating a scan process).
Documented attack patterns abuse exactly the kind of access stop_scan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_scan:
{
"version": "1",
"default": "deny",
"tools": {
"stop_scan": {
"limits": [
{
"counter": "stop_scan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_scan 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 a running security scan. It is categorised as a Execute tool in the AWS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AWS MCP server in PolicyLayer and add a rule for stop_scan: 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.
stop_scan 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_scan 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_scan. 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_scan 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.
Start from AWS, 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.
300 AWS tools catalogued and risk-classified — across an index of 43,000+ MCP servers.