run_accessibility_scan · Navable MCP: Risk & Policy

WHAT IT DOES

What run_accessibility_scan does on Navable MCP

AI agents invoke run_accessibility_scan to trigger actions in Navable MCP. 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 run_accessibility_scan needs a policy

This tool triggers external operations (browser automation and accessibility analysis) rather than simply retrieving static data. Although the scanning itself is read-only in intent, the execution of Playwright commands constitutes triggering code/browser actions.

From the tool's definition Tool description states it 'Scan[s] a URL' and uses 'Playwright + axe-core' — Playwright is a browser automation framework that executes actions in a real browser environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_accessibility_scan Rate-limited

run_accessibility_scan 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": {
    "run_accessibility_scan": {
      "limits": [
        {
          "counter": "run_accessibility_scan_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 Navable MCP, so you can run agents against it safely.

FAQ

Questions about run_accessibility_scan

What does the run_accessibility_scan tool do? +

Scan a URL for WCAG 2.1 Level A + AA accessibility violations using Playwright + axe-core,. It is categorised as a Execute tool in the Navable MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_accessibility_scan? +

Register the Navable MCP server in PolicyLayer and add a rule for run_accessibility_scan: 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 Navable MCP. Nothing to install.

What risk level is run_accessibility_scan? +

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

Can I rate-limit run_accessibility_scan? +

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

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

run_accessibility_scan is provided by the Navable MCP server (web-dna/navable-web-accessibility-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.