Execute JavaScript in the browser console
AI agents invoke playwright_evaluate to trigger actions in Playwright MCP 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.
Executing arbitrary JavaScript in a real browser is a quintessential Execute operation. An AI agent misusing this tool could steal credentials, exfiltrate data from web pages, perform unauthorized actions on behalf of the user, redirect navigation, inject malware, or compromise session security. The blast radius is high because the agent has full programmatic control over the page context.
From the tool's definition Tool description states 'Execute JavaScript in the browser console' — this directly runs arbitrary code in a browser environment with access to the DOM, cookies, local storage, and network requests.
Documented attack patterns abuse exactly the kind of access playwright_evaluate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for playwright_evaluate:
{
"version": "1",
"default": "deny",
"tools": {
"playwright_evaluate": {
"limits": [
{
"counter": "playwright_evaluate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}playwright_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 the browser console. It is categorised as a Execute tool in the Playwright MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright MCP Server MCP server in PolicyLayer and add a rule for playwright_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 Playwright MCP Server. Nothing to install.
playwright_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 playwright_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 playwright_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.
playwright_evaluate is provided by the Playwright MCP Server MCP server (pvinis/mcp-playwright-stealth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP 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.
29 Playwright MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.