step_over · MCP JS Debugger MCP: Risk & Policy

WHAT IT DOES

What step_over does on MCP JS Debugger

AI agents invoke step_over to trigger actions in MCP JS Debugger. 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 step_over needs a policy

This tool controls execution flow in a debugger session, advancing the runtime to the next line. It triggers an external operation (resuming/stepping through code execution) rather than merely reading data or writing stored data. While used in a debugging context, it actively controls program execution which qualifies as Execute. Misuse could cause unintended code execution paths.

From the tool's definition Steps over the current statement to the next line in the same function

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

step_over Rate-limited

step_over 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": {
    "step_over": {
      "limits": [
        {
          "counter": "step_over_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 MCP JS Debugger, so you can run agents against it safely.

FAQ

Questions about step_over

What does the step_over tool do? +

Steps over the current statement to the next line in the same function. It is categorised as a Execute tool in the MCP JS Debugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on step_over? +

Register the MCP JS Debugger MCP server in PolicyLayer and add a rule for step_over: 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 JS Debugger. Nothing to install.

What risk level is step_over? +

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

Can I rate-limit step_over? +

Yes. Add a rate_limit block to the step_over 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 step_over completely? +

Set action: deny in the PolicyLayer policy for step_over. 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 step_over? +

step_over is provided by the MCP JS Debugger MCP server (johngrimes/mcp-js-debugger). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.