List dialogs captured from the page (alert/confirm/prompt/beforeunload).
AI agents call browser.list_dialogs to retrieve information from MCP Playwright Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about dialogs that have appeared on a webpage (alerts, confirms, prompts, beforeunload events). It performs a read-only operation with no state changes, no code execution, and no external effects. The severity is low because dialog state is typically non-sensitive metadata about page interactions.
From the tool's definition Tool name 'list_dialogs' and description 'List dialogs captured from the page' indicate retrieval of dialog state with no modification or side effects.
Attacks that exploit this kind of access
List dialogs captured from the page (alert/confirm/prompt/beforeunload). It is categorised as a Read tool in the MCP Playwright Browser MCP Server, which means it retrieves data without modifying state.
Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for browser.list_dialogs: 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 MCP Playwright Browser. Nothing to install.
browser.list_dialogs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser.list_dialogs 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.list_dialogs. 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.list_dialogs is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →