Ahk run Run an AutoHotkey v2 script, or watch a file and auto-run it after edits.
AI agents invoke AHK_Run to trigger actions in Ahk. 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.
This tool executes arbitrary AutoHotkey scripts whose effects are entirely dependent on script content. AutoHotkey scripts can perform nearly any system operation including keyboard/mouse automation, file manipulation, process control, and registry modification. The 'watch a file and auto-run it after edits' capability compounds the risk by enabling unattended code execution.
From the tool's definition Tool description states 'Run an AutoHotkey v2 script' - directly executes arbitrary code. AutoHotkey is a scripting language capable of system automation, sending keystrokes/clicks, file operations, registry access, and other system-level actions.
Documented attack patterns abuse exactly the kind of access AHK_Run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ahk, and nothing reaches the server without passing your rules. This is the rule we recommend for AHK_Run:
{
"version": "1",
"default": "deny",
"tools": {
"AHK_Run": {
"limits": [
{
"counter": "ahk_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}AHK_Run 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.
Ahk run Run an AutoHotkey v2 script, or watch a file and auto-run it after edits. It is categorised as a Execute tool in the Ahk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ahk MCP server in PolicyLayer and add a rule for AHK_Run: 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 Ahk. Nothing to install.
AHK_Run 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 AHK_Run 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 AHK_Run. 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.
AHK_Run is provided by the Ahk MCP server (truecrimedev/ahk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 40 Ahk tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
40 Ahk tools catalogued and risk-classified — across an index of 42,500+ MCP servers.