drag · BrowserPilot MCP: Risk & Policy

WHAT IT DOES

What drag does on BrowserPilot MCP

AI agents invoke drag to trigger actions in BrowserPilot 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 drag needs a policy

Dragging is a browser automation action that executes a physical UI interaction. Its effects are context-dependent: it could reorder elements, move files, interact with web app widgets, or trigger other operations. This qualifies as Execute since it performs an external browser operation with variable outcomes based on arguments.

From the tool's definition "Drag from one point to another" — triggers a browser interaction (drag action) that performs a UI operation whose effects depend entirely on what element is dragged and where it is dropped.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

drag Rate-limited

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": {
    "drag": {
      "limits": [
        {
          "counter": "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 BrowserPilot MCP, so you can run agents against it safely.

FAQ

Questions about drag

What does the drag tool do? +

Drag from one point to another. It is categorised as a Execute tool in the BrowserPilot 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 drag? +

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

What risk level is drag? +

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

Can I rate-limit drag? +

Yes. Add a rate_limit block to the 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 drag completely? +

Set action: deny in the PolicyLayer policy for 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 drag? +

drag is provided by the BrowserPilot MCP server (sept-7-qi/browserpilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.