Desktop par exact coordinates par click karo (XTEST/XWayland)
AI agents invoke desktop_click to trigger actions in Universal Dev MCP. 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 simulates mouse clicks at arbitrary desktop coordinates via XTEST/XWayland, which is a low-level input injection mechanism. An AI agent could misuse this to interact with any on-screen element, including system dialogs, destructive buttons, or sensitive UI controls.
From the tool's definition 'Desktop par exact coordinates par click karo (XTEST/XWayland)' — executes a mouse click at arbitrary screen coordinates using XTEST/XWayland input injection
Attacks that exploit this kind of access
Desktop par exact coordinates par click karo (XTEST/XWayland). It is categorised as a Execute tool in the Universal Dev MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Universal Dev MCP server in PolicyLayer and add a rule for desktop_click: 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 Universal Dev MCP. Nothing to install.
desktop_click 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 desktop_click 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 desktop_click. 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.
desktop_click is provided by the Universal Dev MCP server (kallusuvaidyam/universal_mcp). 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 →