browser_evaluate_js · DevLab MCP Suite MCP: Risk & Policy

WHAT IT DOES

What browser_evaluate_js does on DevLab MCP Suite

AI agents invoke browser_evaluate_js to trigger actions in DevLab MCP Suite. 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 browser_evaluate_js needs a policy

This tool allows arbitrary JavaScript execution within a browser page context. While JavaScript execution in a controlled testing environment has legitimate uses (inspecting game state, debugging), it carries significant risk if misused by an AI agent without careful guardrails. An agent could use this to exfiltrate data, perform unauthorized actions on web pages, or chain with other tools for broader attacks.

From the tool's definition Tool description states: "Execute JavaScript in the page context and return the result." This directly indicates code execution capability. The mention of "game state inspection, debug hooks" suggests running arbitrary scripts in a browser context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_evaluate_js Rate-limited

browser_evaluate_js 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": {
    "browser_evaluate_js": {
      "limits": [
        {
          "counter": "browser_evaluate_js_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 DevLab MCP Suite, so you can run agents against it safely.

FAQ

Questions about browser_evaluate_js

What does the browser_evaluate_js tool do? +

Execute JavaScript in the page context and return the result. Use for game state inspection, debug hooks, etc. It is categorised as a Execute tool in the DevLab MCP Suite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_evaluate_js? +

Register the DevLab MCP Suite MCP server in PolicyLayer and add a rule for browser_evaluate_js: 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 DevLab MCP Suite. Nothing to install.

What risk level is browser_evaluate_js? +

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

Can I rate-limit browser_evaluate_js? +

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

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

browser_evaluate_js is provided by the DevLab MCP Suite MCP server (tanguito86/devlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.