AI agents invoke aat_run to trigger actions in AWT (AI Watch Tester). 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.
The tool executes Playwright-based browser automation tests against a URL, which is an external operation whose effects depend on the test scenarios and arguments provided. This falls squarely into Execute category. The severity is high because uncontrolled test execution could modify application state, trigger unintended transactions in test environments, or cause resource exhaustion.
From the tool's definition Server description states the system 'runs Playwright tests' and 'self-heals failures automatically.' The tool name 'aat_run' combined with the server's capability to execute automated browser testing indicates this tool triggers test execution.
Documented attack patterns abuse exactly the kind of access aat_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWT (AI Watch Tester), and nothing reaches the server without passing your rules. This is the rule we recommend for aat_run:
{
"version": "1",
"default": "deny",
"tools": {
"aat_run": {
"limits": [
{
"counter": "aat_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}aat_run 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.
aat_run. It is categorised as a Execute tool in the AWT (AI Watch Tester) MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AWT (AI Watch Tester) MCP server in PolicyLayer and add a rule for aat_run: 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 AWT (AI Watch Tester). Nothing to install.
aat_run 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 aat_run 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 aat_run. 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.
aat_run is provided by the AWT (AI Watch Tester) MCP server (ksgisang/ai-watch-tester). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWT (AI Watch Tester), 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.
12 AWT (AI Watch Tester) tools catalogued and risk-classified — across an index of 43,000+ MCP servers.