ira_audit_accessibility · IRA-RESEARCHER MCP: Risk & Policy

WHAT IT DOES

What ira_audit_accessibility does on IRA-RESEARCHER

AI agents invoke ira_audit_accessibility to trigger actions in IRA-RESEARCHER. 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 ira_audit_accessibility needs a policy

This tool executes an operation (accessibility audit) whose effects depend on the browser context and target page. While not destructive or writing data, it runs code-like functionality to analyze and report on page properties. It's Execute rather than Read because it actively runs an audit process (execution) rather than passively retrieving existing data.

From the tool's definition Tool performs 'Run accessibility audit' which executes an automated audit operation on a webpage or browser context, triggering external analysis tools and generating analysis results as a side effect.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ira_audit_accessibility Rate-limited

ira_audit_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": {
    "ira_audit_accessibility": {
      "limits": [
        {
          "counter": "ira_audit_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 IRA-RESEARCHER, so you can run agents against it safely.

FAQ

Questions about ira_audit_accessibility

What does the ira_audit_accessibility tool do? +

Run accessibility audit. It is categorised as a Execute tool in the IRA-RESEARCHER MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ira_audit_accessibility? +

Register the IRA-RESEARCHER MCP server in PolicyLayer and add a rule for ira_audit_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 IRA-RESEARCHER. Nothing to install.

What risk level is ira_audit_accessibility? +

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

Can I rate-limit ira_audit_accessibility? +

Yes. Add a rate_limit block to the ira_audit_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 ira_audit_accessibility completely? +

Set action: deny in the PolicyLayer policy for ira_audit_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 ira_audit_accessibility? +

ira_audit_accessibility is provided by the IRA-RESEARCHER MCP server (neuralnexustech/ira-researcher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.