Press and hold mouse button at current cursor position. For drag-and-drop, prefer os_drag which handles the complete operation. Use os_mouse_down + os_move + os_mouse_up only for complex multi-step drag scenarios.
AI agents invoke os_mouse_down 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 triggers a physical mouse button press action on the desktop, which is a UI interaction/execution operation. It can be used as part of drag-and-drop sequences that could move, manipulate, or interact with any application element. The effect depends on what is under the cursor and how it is combined with subsequent actions, making it an Execute-category tool.
From the tool's definition 'Press and hold mouse button at current cursor position' and 'Use os_mouse_down + os_move + os_mouse_up only for complex multi-step drag scenarios'
Attacks that exploit this kind of access
Press and hold mouse button at current cursor position. For drag-and-drop, prefer os_drag which handles the complete operation. Use os_mouse_down + os_move + os_mouse_up only for complex multi-step drag scenarios. 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_mouse_down: 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_mouse_down 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_mouse_down 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_mouse_down. 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_mouse_down 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 →