AI agents invoke browser_run_code_unsafe to trigger actions in Playwright. 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 runs arbitrary code in the browser (Execute category), and the 'unsafe' designation indicates it permits dangerous operations without safety guardrails. The blast radius is high: an AI could execute malicious scripts, steal credentials, manipulate page content, exfiltrate data, or perform unauthorized actions.
From the tool's definition Tool name 'browser_run_code_unsafe' explicitly indicates code execution capability with 'unsafe' qualifier, suggesting arbitrary code execution in a browser context without restrictions.
Documented attack patterns abuse exactly the kind of access browser_run_code_unsafe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_run_code_unsafe:
{
"version": "1",
"default": "deny",
"tools": {
"browser_run_code_unsafe": {
"limits": [
{
"counter": "browser_run_code_unsafe_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_run_code_unsafe 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.
browser_run_code_unsafe. It is categorised as a Execute tool in the Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_run_code_unsafe: 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. Nothing to install.
browser_run_code_unsafe 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 browser_run_code_unsafe 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 browser_run_code_unsafe. 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.
browser_run_code_unsafe is provided by the Playwright MCP server (@playwright/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright, 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.
68 Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.