test_accessibility · Accessibility MCP Server MCP

WHAT IT DOES

What test_accessibility does on Accessibility MCP Server

AI agents invoke test_accessibility to trigger actions in Accessibility 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_accessibility needs a policy

This tool triggers external browser automation (Playwright) and runs analysis code (axe-core) against a target website. It is not a passive read — it initiates real browser sessions and external network requests. The blast radius is medium: it could be misused to probe arbitrary URLs, consume resources, or trigger unintended interactions on target sites, but it does not modify or delete data.

From the tool's definition 'Run accessibility tests on a website using Playwright and axe-core' — actively launches a browser via Playwright and executes axe-core audits against a remote URL

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

test_accessibility Rate-limited

test_accessibility 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_accessibility": {
      "limits": [
        {
          "counter": "test_accessibility_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 Accessibility MCP Server, so you can run agents against it safely.

FAQ

Questions about test_accessibility

What does the test_accessibility tool do? +

Run accessibility tests on a website using Playwright and axe-core against WCAG standards. It is categorised as a Execute tool in the Accessibility 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_accessibility? +

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

What risk level is test_accessibility? +

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

Can I rate-limit test_accessibility? +

Yes. Add a rate_limit block to the test_accessibility 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_accessibility completely? +

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

test_accessibility is provided by the Accessibility MCP Server MCP server (jbuchan/accessibility-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.