AI agents invoke drag_mouse to trigger actions in Wayland. 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.
The tool name strongly implies a mouse drag action (click, hold, and move), which is an interactive desktop control operation. Like other mouse control siblings on this server, it triggers external operations on the user's desktop environment. The description is empty, lowering confidence, but the naming pattern and server context make Execute the most appropriate category.
From the tool's definition Tool name 'drag_mouse' on a server described as providing 'mouse and keyboard control tools for modern Linux desktops via Wayland'; sibling tools include 'click_mouse', 'move_mouse', 'scroll_mouse'.
Documented attack patterns abuse exactly the kind of access drag_mouse gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wayland, and nothing reaches the server without passing your rules. This is the rule we recommend for drag_mouse:
{
"version": "1",
"default": "deny",
"tools": {
"drag_mouse": {
"limits": [
{
"counter": "drag_mouse_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}drag_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.
drag_mouse. It is categorised as a Execute tool in the Wayland MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Wayland MCP server in PolicyLayer and add a rule for drag_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. Nothing to install.
drag_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 drag_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 drag_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.
drag_mouse is provided by the Wayland MCP server (someaka/wayland-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wayland, 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 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.