debug_step · Polybugger MCP: Risk & Policy

WHAT IT DOES

What debug_step does on Polybugger

AI agents invoke debug_step to trigger actions in Polybugger. 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.

WHY IT NEEDS A POLICY

Why debug_step needs a policy

This tool controls the execution flow of a debugging session by stepping through code line by line or into/out of functions. It triggers external execution operations in a running process, making it an Execute category tool. Misuse could cause unintended program state changes or advance execution past critical breakpoints, but blast radius is limited to the active debug session.

From the tool's definition Step execution: over (next line), into (enter function), out (exit function)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debug_step Rate-limited

debug_step 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "debug_step": {
      "limits": [
        {
          "counter": "debug_step_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Polybugger, so you can run agents against it safely.

FAQ

Questions about debug_step

What does the debug_step tool do? +

Step execution: over (next line), into (enter function), out (exit function). It is categorised as a Execute tool in the Polybugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on debug_step? +

Register the Polybugger MCP server in PolicyLayer and add a rule for debug_step: 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 Polybugger. Nothing to install.

What risk level is debug_step? +

debug_step is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit debug_step? +

Yes. Add a rate_limit block to the debug_step 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.

How do I block debug_step completely? +

Set action: deny in the PolicyLayer policy for debug_step. 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.

What MCP server provides debug_step? +

debug_step is provided by the Polybugger MCP server (wilfoa/polybugger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.