AI agents call aat_diff to retrieve information from AWT (AI Watch Tester) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In an E2E testing framework, diff operations typically retrieve and compare snapshots or results without modifying application state. No evidence of side effects, external command execution, data mutation, or financial impact. Classified as Read due to its diagnostic/query nature, with lower confidence due to the missing description.
From the tool's definition Tool name 'aat_diff' suggests a comparison or differential operation. Given the server's E2E testing context and sibling tools like 'aat_snapshot' and 'aat_validate', this likely compares test outputs or application states.
Documented attack patterns abuse exactly the kind of access aat_diff 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_diff:
{
"version": "1",
"default": "deny",
"tools": {
"aat_diff": {}
}
}aat_diff is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
aat_diff. It is categorised as a Read tool in the AWT (AI Watch Tester) MCP Server, which means it retrieves data without modifying state.
Register the AWT (AI Watch Tester) MCP server in PolicyLayer and add a rule for aat_diff: 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_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the aat_diff 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_diff. 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_diff 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.