Press-and-hold left button at (x1,y1), drag to (x2,y2), release.
AI agents invoke drag to trigger actions in Hermes Computer Use. 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 performs physical mouse drag operations on a live browser instance. It can interact with UI elements, move files, manipulate sliders, reorder content, or trigger drag-and-drop behaviors whose effects depend entirely on the arguments and target context. As part of an anti-bot-evading browser automation suite, misuse could enable unauthorized interactions with web applications at scale.
From the tool's definition Press-and-hold left button at (x1,y1), drag to (x2,y2), release — triggers OS-level mouse drag actions in a real browser
Attacks that exploit this kind of access
Press-and-hold left button at (x1,y1), drag to (x2,y2), release. It is categorised as a Execute tool in the Hermes Computer Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hermes Computer Use 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 Hermes Computer Use. Nothing to install.
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 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 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.
drag is provided by the Hermes Computer Use MCP server (noah3521/hermes-computer-use). 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 →