AI agents invoke browser_handle_dialog to trigger actions in Playwright MCP. 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.
Handling a dialog is an interactive browser action that can accept or dismiss dialogs, potentially confirming destructive or sensitive operations. It falls under Execute as it triggers external browser operations, but the severity is medium since the impact depends on what the underlying dialog was prompting.
From the tool's definition "Handle a dialog" — interacts with browser dialog boxes (alerts, confirms, prompts), triggering external browser UI operations whose effects depend on arguments (e.g., accepting or dismissing dialogs can unblock or cancel pending browser actions).
Documented attack patterns abuse exactly the kind of access browser_handle_dialog gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_handle_dialog:
{
"version": "1",
"default": "deny",
"tools": {
"browser_handle_dialog": {
"limits": [
{
"counter": "browser_handle_dialog_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_handle_dialog 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.
Handle a dialog. It is categorised as a Execute tool in the Playwright MCP 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_handle_dialog: 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. Nothing to install.
browser_handle_dialog 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_handle_dialog 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_handle_dialog. 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_handle_dialog is provided by the Playwright MCP server (korwabs/playwright-record-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright MCP, 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.
32 Playwright MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.