Drag one DOM element to another in Safari — drag-and-drop automation using CSS selectors. Scrolls both elements into view, computes their screen coordinates, then performs the drag. Auto-detects drag method: HTML5 DragEvent API for draggable=
AI agents invoke drag_element to trigger actions in MacWright. 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 triggers browser automation actions (drag-and-drop) in Safari, executing UI interactions that can manipulate web page state. It's an Execute-category tool as it performs external browser operations whose effects depend on the arguments (source/target CSS selectors). The blast radius is medium since it can manipulate web content but is limited to drag-and-drop interactions within Safari.
From the tool's definition Drag one DOM element to another in Safari — drag-and-drop automation using CSS selectors... performs the drag. Auto-detects drag method: HTML5 DragEvent API
Attacks that exploit this kind of access
Drag one DOM element to another in Safari — drag-and-drop automation using CSS selectors. Scrolls both elements into view, computes their screen coordinates, then performs the drag. Auto-detects drag method: HTML5 DragEvent API for draggable=. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright MCP server in PolicyLayer and add a rule for drag_element: 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 MacWright. Nothing to install.
drag_element 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 drag_element 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 drag_element. 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.
drag_element is provided by the MacWright MCP server (ruchit-p/macwright). 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 →