AI agents invoke execute_js to trigger actions in Browser Use Server. 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 allows running arbitrary JavaScript in a webpage, which can read sensitive data, modify page content, interact with APIs, trigger downloads, or perform other side-effectful operations depending on the JavaScript provided.
From the tool's definition Tool name 'execute_js' with description 'Execute JavaScript code on a webpage' clearly indicates execution of arbitrary code in a browser context.
Documented attack patterns abuse exactly the kind of access execute_js gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Browser Use Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_js:
{
"version": "1",
"default": "deny",
"tools": {
"execute_js": {
"limits": [
{
"counter": "execute_js_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_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.
Execute JavaScript code on a webpage. It is categorised as a Execute tool in the Browser Use Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser Use Server MCP server in PolicyLayer and add a rule for execute_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 Browser Use Server. Nothing to install.
execute_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 execute_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 execute_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.
execute_js is provided by the Browser Use Server MCP server (ztobs/cline-browser-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Browser Use Server, 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.
4 Browser Use Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.