# browser_handle_dialog

A execute tool on the Playwright MCP MCP server.

Agent View of the PolicyLayer registry record for `browser_handle_dialog`. HTML page: https://policylayer.com/tools/alialobidm-playwright-mcp/browser-handle-dialog

## Facts

- Tool: `browser_handle_dialog`
- Server: Playwright MCP (`alialobidm/playwright-mcp`) — https://policylayer.com/tools/alialobidm-playwright-mcp.md
- Homepage: https://github.com/alialobidm/playwright-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "browser_handle_dialog",
    "arguments": {}
  }
}
```

## Why browser_handle_dialog is rated High

The tool name suggests it handles browser dialogs (e.g., alert, confirm, prompt). Handling dialogs is an interactive browser action that can trigger confirmations, dismiss warnings, or accept/reject operations with real-world consequences. It fits the Execute category as it triggers browser interactions. Confidence is reduced because the description is empty, leaving the exact behavior ambiguous.

From the tool's own definition: "Tool name 'browser_handle_dialog' on a browser automation server (Playwright MCP) that 'provides browser automation capabilities' and allows LLMs to 'interact with web pages'."

## Use case

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.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Playwright MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_handle_dialog": {
      "limits": [
        {
          "counter": "browser_handle_dialog_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Playwright MCP (58)

- `browser_cookie_clear` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-cookie-clear.md
- `browser_cookie_delete` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-cookie-delete.md
- `browser_localstorage_clear` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-localstorage-clear.md
- `browser_localstorage_delete` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-localstorage-delete.md
- `browser_sessionstorage_clear` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-sessionstorage-clear.md
- `browser_sessionstorage_delete` — Destructive — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-sessionstorage-delete.md
- `browser_click` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-click.md
- `browser_close` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-close.md
- `browser_drag` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-drag.md
- `browser_evaluate` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-evaluate.md
- `browser_file_upload` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-file-upload.md
- `browser_fill_form` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-fill-form.md
- `browser_hover` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-hover.md
- `browser_install` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-install.md
- `browser_mouse_click_xy` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-click-xy.md
- `browser_mouse_down` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-down.md
- `browser_mouse_drag_xy` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-drag-xy.md
- `browser_mouse_move_xy` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-move-xy.md
- `browser_mouse_up` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-up.md
- `browser_mouse_wheel` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-mouse-wheel.md
- `browser_navigate` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-navigate.md
- `browser_navigate_back` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-navigate-back.md
- `browser_press_key` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-press-key.md
- `browser_resize` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-resize.md
- `browser_route` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-route.md
- `browser_run_code` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-run-code.md
- `browser_select_option` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-select-option.md
- `browser_start_tracing` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-start-tracing.md
- `browser_start_video` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-start-video.md
- `browser_stop_tracing` — Execute — https://policylayer.com/tools/alialobidm-playwright-mcp/browser-stop-tracing.md
- …and 28 more: https://policylayer.com/tools/alialobidm-playwright-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=alialobidm-playwright-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/alialobidm-playwright-mcp