test_keyboard · aria51 MCP Server MCP: Risk & Policy

WHAT IT DOES

What test_keyboard does on aria51 MCP Server

AI agents invoke test_keyboard to trigger actions in aria51 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.

WHY IT NEEDS A POLICY

Why test_keyboard needs a policy

The tool executes browser actions (pressing Tab, analyzing focus) on a web page, which constitutes running external operations. It does not merely retrieve static data; it actively drives browser behavior. Misuse risk is moderate — it interacts with live pages but does not modify data or incur financial consequences.

From the tool's definition 'Test keyboard navigation on a page by pressing Tab and analyzing focus behavior' — actively simulates keyboard input (Tab presses) and analyzes focus behavior on a live page, triggering browser interactions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

test_keyboard Rate-limited

test_keyboard 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "test_keyboard": {
      "limits": [
        {
          "counter": "test_keyboard_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches aria51 MCP Server, so you can run agents against it safely.

FAQ

Questions about test_keyboard

What does the test_keyboard tool do? +

Test keyboard navigation on a page by pressing Tab and analyzing focus behavior. Returns tab order, focus trap detection, focus indicator presence, and skip link status. Use for WCAG 2.1.1, 2.1.2, 2.4.1, 2.4.3, 2.4.7 checks. Set deep=true for AI-enhanced analysis (requires OPENAI_API_KEY). It is categorised as a Execute tool in the aria51 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on test_keyboard? +

Register the aria51 MCP Server MCP server in PolicyLayer and add a rule for test_keyboard: 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 aria51 MCP Server. Nothing to install.

What risk level is test_keyboard? +

test_keyboard is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit test_keyboard? +

Yes. Add a rate_limit block to the test_keyboard 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 test_keyboard completely? +

Set action: deny in the PolicyLayer policy for test_keyboard. 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 test_keyboard? +

test_keyboard is provided by the aria51 MCP Server MCP server (justinleeirizarry/aria51). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.