bytebot_drag · ByteBot MCP Server MCP: Risk & Policy

WHAT IT DOES

What bytebot_drag does on ByteBot MCP Server

AI agents invoke bytebot_drag to trigger actions in ByteBot MCP Server. 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 bytebot_drag needs a policy

This tool executes a mouse drag action on the desktop, which is a physical interaction with the UI. It falls under Execute because it triggers external operations (UI manipulation) whose effects depend on the arguments (source/destination coordinates). While a single drag is typically reversible, it can be used to move/drop files, reorder UI elements, or perform other operations with variable consequences.

From the tool's definition 'Drag the mouse from one position to another' and 'moving windows, selecting text, or drag-and-drop operations' — this triggers direct desktop computer control through physical mouse interaction

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bytebot_drag Rate-limited

bytebot_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": {
    "bytebot_drag": {
      "limits": [
        {
          "counter": "bytebot_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 ByteBot MCP Server, so you can run agents against it safely.

FAQ

Questions about bytebot_drag

What does the bytebot_drag tool do? +

Drag the mouse from one position to another. Useful for moving windows, selecting text, or drag-and-drop operations. It is categorised as a Execute tool in the ByteBot MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bytebot_drag? +

Register the ByteBot MCP Server MCP server in PolicyLayer and add a rule for bytebot_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 ByteBot MCP Server. Nothing to install.

What risk level is bytebot_drag? +

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

Can I rate-limit bytebot_drag? +

Yes. Add a rate_limit block to the bytebot_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 bytebot_drag completely? +

Set action: deny in the PolicyLayer policy for bytebot_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 bytebot_drag? +

bytebot_drag is provided by the ByteBot MCP Server MCP server (sensuslab/spark-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.