AI agents invoke browser_move_mouse 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.
Moving the mouse is a browser automation action that executes an operation in a remote headless browser. While it has no direct side effects on its own, it is an Execute-class action as it triggers external browser operations. It is lower severity since mouse movement alone without clicking rarely causes harm, but in context of an agent chain it can prepare for drag operations or hover-triggered UI changes.
From the tool's definition 'Move the mouse to specific coordinates without clicking' — triggers a browser action (mouse movement) in a controlled headless browser environment
Attacks that exploit this kind of access
Move the mouse to specific coordinates without clicking. Coordinates are RELATIVE (0-1 range). Useful for hovering or preparing for drag operations. 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_move_mouse: 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_move_mouse 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_move_mouse 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_move_mouse. 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_move_mouse 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 →