AI agents invoke click_mouse to trigger actions in Wayland MCP Server. 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.
Clicking the mouse triggers UI interactions (button presses, link clicks, form submissions, etc.) that can cause external operations with effects entirely dependent on what is on screen at the time. This is an active desktop automation action, not a passive read. Severity is medium because a misplaced click could trigger unintended actions, but the blast radius is bounded by what the current UI exposes.
From the tool's definition Simulate left mouse click at current position
Documented attack patterns abuse exactly the kind of access click_mouse gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wayland MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for click_mouse:
{
"version": "1",
"default": "deny",
"tools": {
"click_mouse": {
"limits": [
{
"counter": "click_mouse_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}click_mouse stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Simulate left mouse click at current position. It is categorised as a Execute tool in the Wayland MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wayland MCP Server MCP server in PolicyLayer and add a rule for click_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 Wayland MCP Server. Nothing to install.
click_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 click_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 click_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.
click_mouse is provided by the Wayland MCP Server MCP server (kurojs/wayland-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wayland MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 Wayland MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.