evaluate_script

THE RISK

High Risk

Why evaluate_script needs a policy

This tool executes arbitrary JavaScript code in the context of a live browser page. An AI agent could misuse it to exfiltrate data, manipulate the DOM, perform authenticated actions, access cookies/storage, or interact with any APIs available in the page's JavaScript environment. The blast radius is high because execution is arbitrary and context-dependent.

From the tool's definition Evaluate a JavaScript function inside the currently selected page

Documented attack patterns abuse exactly the kind of access evaluate_script gives an agent:

POLICY

How to control evaluate_script

PolicyLayer is an MCP gateway — it sits between your AI agents and JS Reverse Strong MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_script:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate_script": {
      "limits": [
        {
          "counter": "evaluate_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

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.

Create a free account and register JS Reverse Strong MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More JS Reverse Strong MCP tools

Destructive delete_session_state Delete one in-memory session snapshot by sessionId. Destructive remove_hook Remove a hook by id. Execute evaluate_on_callframe Evaluates a JavaScript expression in the context of a specific call frame while paused. Th Execute inject_preload_script Register a JavaScript snippet that will run on future document loads before page scripts e Execute navigate_page Navigates the currently selected page to a URL, or performs back/forward/reload navigation Execute new_page Creates a new page and navigates to the specified URL. Waits for DOMContentLoaded event (n Execute stop_monitor Stops an event monitor. Execute wait_for_element Wait for selector to appear.

All 85 JS Reverse Strong MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in JS Reverse Strong MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about evaluate_script

What does the evaluate_script tool do? +

Evaluate a JavaScript function inside the currently selected page. Returns the response as JSON so returned values have to JSON-serializable. It is categorised as a Execute tool in the JS Reverse Strong 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 JS Reverse Strong 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 JS Reverse Strong 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 JS Reverse Strong MCP server (lwjjike/jsreverser-strong-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every JS Reverse Strong MCP tool call.

Start from JS Reverse Strong MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →