Perform a drag-and-drop operation: moves to start position, holds mouse button, smoothly drags to destination, then releases. Use this for moving files, reordering items, resizing windows, or any UI interaction requiring drag-and-drop.
AI agents invoke os_drag to trigger actions in OScribe. 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.
This tool executes UI automation actions (drag-and-drop) that can have wide-ranging side effects depending on what is being dragged. Moving files could displace or overwrite data, reordering items modifies application state, and resizing windows alters UI configuration. It is an Execute-category tool because its effects depend entirely on what arguments are passed and what is being interacted with on screen.
From the tool's definition 'Perform a drag-and-drop operation: moves to start position, holds mouse button, smoothly drags to destination, then releases. Use this for moving files, reordering items, resizing windows, or any UI interaction requiring drag-and-drop.'
Attacks that exploit this kind of access
Perform a drag-and-drop operation: moves to start position, holds mouse button, smoothly drags to destination, then releases. Use this for moving files, reordering items, resizing windows, or any UI interaction requiring drag-and-drop. It is categorised as a Execute tool in the OScribe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OScribe MCP server in PolicyLayer and add a rule for os_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 OScribe. Nothing to install.
os_drag is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the os_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.
Set action: deny in the PolicyLayer policy for os_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.
os_drag is provided by the OScribe MCP server (mikealkeal/oscribe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →