evaluate_javascript · MCP Connect MCP: Risk & Policy

WHAT IT DOES

What evaluate_javascript does on MCP Connect

AI agents invoke evaluate_javascript to trigger actions in MCP Connect. 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 evaluate_javascript needs a policy

This tool falls under Execute because it runs arbitrary code whose effects depend on the supplied JavaScript arguments. While JavaScript in a browser has limited access (no direct file-system access on the host), it can still modify DOM, steal session data, exfiltrate information, perform unauthorized API calls, or trigger phishing actions.

From the tool's definition 'Execute JavaScript code in page context' permits arbitrary JavaScript execution within a browser context, enabling the tool to trigger side effects dependent on the argument (the code to execute).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_javascript Rate-limited

evaluate_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": {
    "evaluate_javascript": {
      "limits": [
        {
          "counter": "evaluate_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 MCP Connect, so you can run agents against it safely.

FAQ

Questions about evaluate_javascript

What does the evaluate_javascript tool do? +

Execute JavaScript code in page context. It is categorised as a Execute tool in the MCP Connect MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on evaluate_javascript? +

Register the MCP Connect MCP server in PolicyLayer and add a rule for evaluate_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 MCP Connect. Nothing to install.

What risk level is evaluate_javascript? +

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

Can I rate-limit evaluate_javascript? +

Yes. Add a rate_limit block to the evaluate_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 evaluate_javascript completely? +

Set action: deny in the PolicyLayer policy for evaluate_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 evaluate_javascript? +

evaluate_javascript is provided by the MCP Connect MCP server (plaintest/mcp-connect). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.