browser_screen_drag · Playwright MCP: Risk & Policy

WHAT IT DOES

What browser_screen_drag does on Playwright MCP

AI agents invoke browser_screen_drag 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.

WHY IT NEEDS A POLICY

Why browser_screen_drag needs a policy

Dragging within a browser can trigger arbitrary UI interactions such as reordering items, moving files, drawing, or activating controls. This is a browser action with side effects dependent on arguments, placing it firmly in the Execute category. Severity is high because in an automated browser context, such actions can affect web applications, submit forms indirectly, or manipulate sensitive UI components.

From the tool's definition 'Drag left mouse button' — triggers a direct browser interaction (mouse drag action) that can manipulate UI elements, move items, trigger drag-and-drop operations, or interact with web applications in ways whose effects depend on the target elements and…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_screen_drag Rate-limited

browser_screen_drag 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_screen_drag": {
      "limits": [
        {
          "counter": "browser_screen_drag_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Playwright MCP, so you can run agents against it safely.

FAQ

Questions about browser_screen_drag

What does the browser_screen_drag tool do? +

Drag left mouse button. 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.

How do I enforce a policy on browser_screen_drag? +

Register the Playwright MCP server in PolicyLayer and add a rule for browser_screen_drag: 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.

What risk level is browser_screen_drag? +

browser_screen_drag is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_screen_drag? +

Yes. Add a rate_limit block to the browser_screen_drag 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.

How do I block browser_screen_drag completely? +

Set action: deny in the PolicyLayer policy for browser_screen_drag. 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.

What MCP server provides browser_screen_drag? +

browser_screen_drag is provided by the Playwright MCP server (markbustamante77/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.