AI agents invoke runAs 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.
runAs executes external programs or scripts, which is an Execute-category action whose effects depend on what program/arguments are passed. While it could potentially be Destructive if used to run deletion commands, the primary capability is execution control, making it Execute-severity high due to potential for privilege escalation and arbitrary code execution with elevated credentials.
From the tool's definition Tool name 'runAs' on a Windows Desktop Automation server that wraps AutoIt functionality. AutoIt's RunAs function executes a program with elevated privileges or under a different user context.
Documented attack patterns abuse exactly the kind of access runAs 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 runAs:
{
"version": "1",
"default": "deny",
"tools": {
"runAs": {
"limits": [
{
"counter": "runas_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}runAs 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.
runAs. 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 runAs: 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.
runAs 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 runAs 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 runAs. 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.
runAs 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.