step · Rr MCP: Risk & Policy

WHAT IT DOES

What step does on Rr

AI agents invoke step to trigger actions in Rr. 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 needs a policy

This tool advances execution in a debugger session, triggering program state changes by executing code step by step. It is an execution control action within a live debugging session, not merely reading data. Misuse could advance execution past critical points or trigger unintended side effects in the debugged program.

From the tool's definition Step forward one source line, entering into function calls

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

step Rate-limited

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": {
    "step": {
      "limits": [
        {
          "counter": "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 Rr, so you can run agents against it safely.

FAQ

Questions about step

What does the step tool do? +

Step forward one source line, entering into function calls. It is categorised as a Execute tool in the Rr 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? +

Register the Rr MCP server in PolicyLayer and add a rule for 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 Rr. Nothing to install.

What risk level is step? +

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

Can I rate-limit step? +

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

Set action: deny in the PolicyLayer policy for 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 step? +

step is provided by the Rr MCP server (jnjaeschke/rr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.