AutoHotkey v2 debugger via DBGp protocol. Enables autonomous debugging: capture errors, analyze them, and auto-apply fixes. Actions: - start: Start DBGp listener (waits for AHK /Debug connection) - stop: Stop DBGp listener - status: Get connection status - run: Continue execution - step_into/step...
AI agents invoke AHK_Debug_DBGp 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 can execute and control running AHK processes via the DBGp debug protocol, step through code execution, and critically can auto-apply code fixes directly to files. The combination of controlling program execution and modifying source files represents a high-severity Execute (bordering on Write) capability.
From the tool's definition 'autonomous debugging: capture errors, analyze them, and auto-apply fixes', 'apply_fix: Auto-apply code fix to file', 'step_into/step_over/step_out: Step debugging', 'run: Continue execution'
Documented attack patterns abuse exactly the kind of access AHK_Debug_DBGp 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_Debug_DBGp:
{
"version": "1",
"default": "deny",
"tools": {
"AHK_Debug_DBGp": {
"limits": [
{
"counter": "ahk_debug_dbgp_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}AHK_Debug_DBGp 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.
AutoHotkey v2 debugger via DBGp protocol. Enables autonomous debugging: capture errors, analyze them, and auto-apply fixes. Actions: - start: Start DBGp listener (waits for AHK /Debug connection) - stop: Stop DBGp listener - status: Get connection status - run: Continue execution - step_into/step_over/step_out: Step debugging - capture_error: Wait for next error with full context - analyze_error: Build analysis prompt from error - apply_fix: Auto-apply code fix to file - list_errors/clear_errors: Manage error queue - get_source: Get source lines around a line - breakpoint_set/remove/list: Manage breakpoints - variables_get: Get variables (context: 0=local, 1=global) - evaluate: Evaluate expression - stack_trace: Get call stack. 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_Debug_DBGp: 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_Debug_DBGp 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_Debug_DBGp 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_Debug_DBGp. 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_Debug_DBGp 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.