AI agents invoke evaluate_js to trigger actions in Camoufox Reverse. 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.
'evaluate_js' almost certainly executes arbitrary JavaScript code in the browser context. The server description explicitly mentions dynamic debugging, function hooking, and bypassing bot detection, making this a high-capability code execution tool. Misuse could allow arbitrary JS execution in browser sessions, exfiltration of cookies/credentials, DOM manipulation, and more.
From the tool's definition Tool name 'evaluate_js' on a server described as enabling 'dynamic debugging, function hooking, and network interception' with JavaScript reverse engineering capabilities
Documented attack patterns abuse exactly the kind of access evaluate_js gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Camoufox Reverse, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_js:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_js": {
"limits": [
{
"counter": "evaluate_js_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
evaluate_js. It is categorised as a Execute tool in the Camoufox Reverse MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Camoufox Reverse MCP server in PolicyLayer and add a rule for 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 Camoufox Reverse. Nothing to install.
evaluate_js is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
evaluate_js is provided by the Camoufox Reverse MCP server (whitenightshadow/camoufox-reverse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 36 Camoufox Reverse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
36 Camoufox Reverse tools catalogued and risk-classified — across an index of 42,500+ MCP servers.