frame_evaluate

THE RISK

High Risk

Why frame_evaluate needs a policy

This tool executes arbitrary JavaScript within browser frames, which is a classic Execute category action. The blast radius is critical because: (1) JavaScript execution can read sensitive data, modify page content, steal credentials, or trigger unintended actions; (2) it operates within the context of whatever site is loaded, potentially accessing cookies, local storage, and sensitive information; (3) combined with…

From the tool's definition Tool name 'frame_evaluate' combined with description 'Execute JavaScript inside a specific frame/iframe' directly indicates code execution capability.

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

POLICY

How to control frame_evaluate

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

policy.json

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

frame_evaluate 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 MCP Camoufox — 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 MCP Camoufox tools

Destructive cookie_delete Delete cookies. Both empty = clear all. Destructive localstorage_clear Clear all localStorage. Destructive reset_profile Delete the persistent profile (~/.camoufox-mcp/profile) entirely. Destructive browser_close Close the browser. Cookies are preserved in the persistent profile (~/.camoufox-mcp/profil Destructive tab_close Close a tab by index (-1 = active), or by url_contains. Execute batch_actions Execute multiple actions in one call. Each action: {type, ref?, value?, text?, key?, url?} Execute browser_launch Launch Camoufox stealth browser and navigate to URL. Browser persists between calls. Execute evaluate Execute JavaScript in page context.

All 102 MCP Camoufox 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 MCP Camoufox → 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 frame_evaluate

What does the frame_evaluate tool do? +

Execute JavaScript inside a specific frame/iframe. It is categorised as a Execute tool in the MCP Camoufox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on frame_evaluate? +

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

What risk level is frame_evaluate? +

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

Can I rate-limit frame_evaluate? +

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

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

frame_evaluate is provided by the MCP Camoufox MCP server (robithyusuf/mcp-camoufox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Camoufox tool call.

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

CHECK YOUR STACK →