ira_javascript · IRA-RESEARCHER MCP: Risk & Policy

WHAT IT DOES

What ira_javascript does on IRA-RESEARCHER

AI agents invoke ira_javascript 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_javascript needs a policy

This tool allows JavaScript execution, which is a fundamental Execute capability. Combined with the server's full DevTools access and stealth mode, malicious JavaScript could exfiltrate credentials, session tokens, form data, or trigger actions impersonating the user. Severity is critical due to unrestricted code execution in an authenticated browser context with no apparent sandboxing or safety constraints.

From the tool's definition Execute JavaScript in page. JavaScript execution enables arbitrary code to run in browser context with full access to DOM, network APIs, local storage, and sensitive page data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ira_javascript Rate-limited

ira_javascript 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_javascript": {
      "limits": [
        {
          "counter": "ira_javascript_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_javascript

What does the ira_javascript tool do? +

Execute JavaScript in page. 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_javascript? +

Register the IRA-RESEARCHER MCP server in PolicyLayer and add a rule for ira_javascript: 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_javascript? +

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

Can I rate-limit ira_javascript? +

Yes. Add a rate_limit block to the ira_javascript 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_javascript completely? +

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

ira_javascript 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.