AI agents invoke keyboard_type to trigger actions in Kwin. 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 'keyboard_type' strongly suggests it simulates keyboard input by typing text into a desktop application. This constitutes executing an action on an external system (the desktop GUI). Sibling tools like 'keyboard_key', 'keyboard_key_down', 'keyboard_key_up' confirm this is an input simulation suite.
From the tool's definition Tool name 'keyboard_type' on a server designed to 'automate Linux desktop GUI' by 'interacting with Wayland applications'
Documented attack patterns abuse exactly the kind of access keyboard_type gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kwin, and nothing reaches the server without passing your rules. This is the rule we recommend for keyboard_type:
{
"version": "1",
"default": "deny",
"tools": {
"keyboard_type": {
"limits": [
{
"counter": "keyboard_type_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}keyboard_type 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.
keyboard_type. It is categorised as a Execute tool in the Kwin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kwin MCP server in PolicyLayer and add a rule for keyboard_type: 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 Kwin. Nothing to install.
keyboard_type 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 keyboard_type 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 keyboard_type. 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.
keyboard_type is provided by the Kwin MCP server (isac322/kwin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kwin, 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.
30 Kwin tools catalogued and risk-classified — across an index of 43,000+ MCP servers.