AI agents invoke stop_scan to trigger actions in AWS Labs CloudTrail 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 a running scan is an execute action that triggers an external operation (halting an AWS security scanning process). It is not read-only (no data retrieval), not write (not creating/modifying persistent data), not destructive (the scan can be restarted), and not financial.
From the tool's definition The tool description states it 'Stop[s] a running security scan' — an action that interrupts an active operation whose consequences depend on the context and timing of when the scan is terminated.
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 Labs CloudTrail MCP Server, 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 Labs CloudTrail MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AWS Labs CloudTrail MCP Server 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 Labs CloudTrail MCP Server. 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 Labs CloudTrail MCP Server MCP server (awslabs.cloudtrail-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 CloudTrail 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 CloudTrail MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.