AI agents invoke browser_drag to trigger actions in MCProxy. 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 a browser UI action (drag gesture) that triggers external operations in a controlled headless browser. The effects depend on what element is being dragged and the context (e.g., moving files, manipulating UI controls, drawing). It falls under Execute as it performs browser interactions whose consequences vary by arguments and target page state.
From the tool's definition 'Drag from one coordinate to another' and 'Useful for sliders, drag-and-drop, and drawing' — triggers browser interaction/actions in a headless browser
Attacks that exploit this kind of access
Drag from one coordinate to another. All coordinates are RELATIVE (0-1 range). Useful for sliders, drag-and-drop, and drawing. It is categorised as a Execute tool in the MCProxy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCProxy MCP server in PolicyLayer and add a rule for browser_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 MCProxy. Nothing to install.
browser_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 browser_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 browser_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.
browser_drag is provided by the MCProxy MCP server (saladtechnologies/mcproxy). 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 →