Execute JavaScript code and return the result
AI agents invoke evaluateWithReturn to trigger actions in PlayMCP Browser Automation 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.
The tool permits execution of arbitrary code (JavaScript) whose effects are entirely dependent on the supplied arguments. This is a classic Execute category tool. Severity is high because JavaScript execution in a browser can access cookies, localStorage, session data, exfiltrate credentials, modify page content, or interact with third-party APIs.
From the tool's definition Tool name and description: 'Execute JavaScript code and return the result' — this directly executes arbitrary JavaScript in a browser context, which can read sensitive data, modify the DOM, interact with web services, or trigger side effects depending on the…
Documented attack patterns abuse exactly the kind of access evaluateWithReturn gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PlayMCP Browser Automation Server, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluateWithReturn:
{
"version": "1",
"default": "deny",
"tools": {
"evaluateWithReturn": {
"limits": [
{
"counter": "evaluatewithreturn_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluateWithReturn 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 and return the result. It is categorised as a Execute tool in the PlayMCP Browser Automation Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PlayMCP Browser Automation Server MCP server in PolicyLayer and add a rule for evaluateWithReturn: 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 PlayMCP Browser Automation Server. Nothing to install.
evaluateWithReturn 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 evaluateWithReturn 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 evaluateWithReturn. 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.
evaluateWithReturn is provided by the PlayMCP Browser Automation Server MCP server (jomon003/playmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PlayMCP Browser Automation 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.
38 PlayMCP Browser Automation Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.