evaluate_script · BrowserPilot MCP: Risk & Policy

WHAT IT DOES

What evaluate_script does on BrowserPilot MCP

AI agents invoke evaluate_script to trigger actions in BrowserPilot 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 evaluate_script needs a policy

This tool executes arbitrary JavaScript in the context of a browser page via the Chrome extension scripting API. An AI agent could use this to run any code in the browser context, including exfiltrating data, manipulating DOM, making network requests, stealing cookies/credentials, or performing any action the page's origin is permitted to do.

From the tool's definition Evaluate JavaScript on the page via chrome.scripting.executeScript

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_script Rate-limited

evaluate_script 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_script": {
      "limits": [
        {
          "counter": "evaluate_script_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 BrowserPilot MCP, so you can run agents against it safely.

FAQ

Questions about evaluate_script

What does the evaluate_script tool do? +

Evaluate JavaScript on the page via chrome.scripting.executeScript. The script runs with extension execution semantics and must return a JSON-serializable value; returnByValue is accepted for API compatibility but the extension always returns the serialized result value. It is categorised as a Execute tool in the BrowserPilot 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 evaluate_script? +

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

What risk level is evaluate_script? +

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

Can I rate-limit evaluate_script? +

Yes. Add a rate_limit block to the evaluate_script 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_script completely? +

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

evaluate_script is provided by the BrowserPilot MCP server (sept-7-qi/browserpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.