AI agents invoke controlSend to trigger actions in MCP Windows Desktop Automation. 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.
Based on the server context (AutoIt Windows automation) and the tool name 'controlSend', this almost certainly sends keystrokes or input to a specific window control — a standard AutoIt function (ControlSend). This constitutes executing an action on the desktop by injecting input into UI controls, which can trigger arbitrary application behavior.
From the tool's definition Tool name 'controlSend' on a Windows Desktop Automation server wrapping AutoIt functionality; sibling tools include keyboard/mouse operations, window management, and UI control interactions.
Documented attack patterns abuse exactly the kind of access controlSend gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Windows Desktop Automation, and nothing reaches the server without passing your rules. This is the rule we recommend for controlSend:
{
"version": "1",
"default": "deny",
"tools": {
"controlSend": {
"limits": [
{
"counter": "controlsend_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}controlSend 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.
controlSend. It is categorised as a Execute tool in the MCP Windows Desktop Automation MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Windows Desktop Automation MCP server in PolicyLayer and add a rule for controlSend: 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 MCP Windows Desktop Automation. Nothing to install.
controlSend 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 controlSend 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 controlSend. 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.
controlSend is provided by the MCP Windows Desktop Automation MCP server (mario-andreschak/mcp-windows-desktop-automation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Windows Desktop Automation, 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.
50 MCP Windows Desktop Automation tools catalogued and risk-classified — across an index of 43,000+ MCP servers.