AI agents invoke step_debug to trigger actions in Node Js Debugger MCP Server. 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 controls active code execution by stepping through it (step into/over/out), which directly manipulates a running process's execution flow. It falls under Execute as it triggers external operations on a live Node.js process. Severity is medium because while it doesn't delete data, misuse could disrupt running processes or expose sensitive runtime state.
From the tool's definition Step through code execution
Documented attack patterns abuse exactly the kind of access step_debug gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Node Js Debugger MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for step_debug:
{
"version": "1",
"default": "deny",
"tools": {
"step_debug": {
"limits": [
{
"counter": "step_debug_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}step_debug 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.
Step through code execution. It is categorised as a Execute tool in the Node Js Debugger MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Node Js Debugger MCP Server MCP server in PolicyLayer and add a rule for step_debug: 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 Node Js Debugger MCP Server. Nothing to install.
step_debug 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 step_debug 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 step_debug. 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.
step_debug is provided by the Node Js Debugger MCP Server MCP server (qckfx/node-debugger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Node Js Debugger MCP Server, 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.
8 Node Js Debugger MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.