browser_drag · Byob MCP: Risk & Policy

WHAT IT DOES

What browser_drag does on Byob

AI agents invoke browser_drag to trigger actions in Byob. 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_drag needs a policy

Browser drag actions execute UI interactions in a real Chrome browser using the user's logged-in sessions. While the description is incomplete, dragging can trigger arbitrary UI effects (e.g., drag-and-drop file uploads, reordering items, interacting with web apps).

From the tool's definition 'Drag the mouse from' — the description is truncated/uninformative, but the tool name 'browser_drag' combined with the server's stated capability to 'control your real Chrome browser' to perform 'clicking' and similar browser actions indicates this executes a…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_drag Rate-limited

browser_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_drag": {
      "limits": [
        {
          "counter": "browser_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 Byob, so you can run agents against it safely.

FAQ

Questions about browser_drag

What does the browser_drag tool do? +

Drag the mouse from. It is categorised as a Execute tool in the Byob 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_drag? +

Register the Byob MCP server in PolicyLayer and add a rule for browser_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 Byob. Nothing to install.

What risk level is browser_drag? +

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

Can I rate-limit browser_drag? +

Yes. Add a rate_limit block to the browser_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_drag completely? +

Set action: deny in the PolicyLayer policy for browser_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_drag? +

browser_drag is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.