AI agents invoke evaluate to trigger actions in MCP Camoufox. 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.
This tool permits execution of arbitrary JavaScript in the page context, which can read sensitive data, modify page content, exfiltrate cookies/tokens, or perform any action the page JavaScript can perform.
From the tool's definition Tool name 'evaluate' with description 'Execute JavaScript in page context' explicitly indicates arbitrary code execution within the browser environment.
Documented attack patterns abuse exactly the kind of access evaluate gives an agent:
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 evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate": {
"limits": [
{
"counter": "evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Execute JavaScript in page context. 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.
Register the MCP Camoufox MCP server in PolicyLayer and add a rule for 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.
evaluate 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 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. 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 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.
Start from MCP Camoufox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
102 MCP Camoufox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.