browser_mouse_drag · Browser MCP: Risk & Policy

WHAT IT DOES

What browser_mouse_drag does on Browser

AI agents invoke browser_mouse_drag to trigger actions in Browser. 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_mouse_drag needs a policy

Performing a mouse drag is a browser interaction/action that triggers external operations in the browser (e.g., dragging UI elements, files, or canvas objects). It is an Execute-category action as it causes side effects in the browser environment whose impact depends on arguments (source and destination coordinates/elements).

From the tool's definition Drag from one position to another

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_mouse_drag Rate-limited

browser_mouse_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_mouse_drag": {
      "limits": [
        {
          "counter": "browser_mouse_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 Browser, so you can run agents against it safely.

FAQ

Questions about browser_mouse_drag

What does the browser_mouse_drag tool do? +

Drag from one position to another (see browser_docs). It is categorised as a Execute tool in the Browser 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_mouse_drag? +

Register the Browser MCP server in PolicyLayer and add a rule for browser_mouse_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 Browser. Nothing to install.

What risk level is browser_mouse_drag? +

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

Can I rate-limit browser_mouse_drag? +

Yes. Add a rate_limit block to the browser_mouse_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_mouse_drag completely? +

Set action: deny in the PolicyLayer policy for browser_mouse_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_mouse_drag? +

browser_mouse_drag is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.