Evaluate a JavaScript expression in the page context and return the result.
AI agents invoke evaluate to trigger actions in Webclaw. 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 executes arbitrary JavaScript in the browser page context, giving full access to the DOM, cookies, local storage, network requests, and any other page resources. An AI agent could use this to exfiltrate data, perform unauthorized actions, manipulate page content, or attack the user's session. This is the most dangerous class of Execute tool with critical blast radius.
From the tool's definition Evaluate a JavaScript expression in the page context and return the result.
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 Webclaw, 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.
Evaluate a JavaScript expression in the page context and return the result. It is categorised as a Execute tool in the Webclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Webclaw 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 Webclaw. 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 Webclaw MCP server (kuroko1t/webclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Webclaw, 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.
21 Webclaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.