aat_cost

THE RISK

Low Risk

Why aat_cost needs a policy

This tool retrieves historical or current cost information—a query operation with no side effects, no code execution, no data modification, and no financial transactions. It simply displays metrics about API usage that has already occurred. Classification as Read is appropriate.

From the tool's definition Tool name 'aat_cost' and description 'View AWT AI API usage costs' indicate a read-only operation that retrieves usage/cost data without modifying or executing anything.

Documented attack patterns abuse exactly the kind of access aat_cost gives an agent:

POLICY

How to control aat_cost

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_cost:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "aat_cost": {}
  }
}

aat_cost is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register AWT (AI Watch Tester) — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More AWT (AI Watch Tester) tools

Execute aat_run aat_run Execute aat_run_skill_mode aat_run_skill_mode Execute aat_devqa aat_devqa Execute aat_scan aat_scan Execute aat_watch aat_watch Execute aat_generate_from_doc aat_generate_from_doc Read aat_diff aat_diff Read aat_doctor Check AWT environment and dependencies.

All 12 AWT (AI Watch Tester) tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about aat_cost

What does the aat_cost tool do? +

View AWT AI API usage costs. It is categorised as a Read tool in the AWT (AI Watch Tester) MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on aat_cost? +

Register the AWT (AI Watch Tester) MCP server in PolicyLayer and add a rule for aat_cost: 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.

What risk level is aat_cost? +

aat_cost is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit aat_cost? +

Yes. Add a rate_limit block to the aat_cost 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.

How do I block aat_cost completely? +

Set action: deny in the PolicyLayer policy for aat_cost. 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.

What MCP server provides aat_cost? +

aat_cost 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.

Enforce policy on every AWT (AI Watch Tester) tool call.

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.

CHECK YOUR STACK →