reverse_next · Rr MCP: Risk & Policy

WHAT IT DOES

What reverse_next does on Rr

AI agents invoke reverse_next 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 reverse_next needs a policy

This tool controls execution of a debugging session by stepping backward through program execution. It triggers external operations (reverse execution in an rr debugging session) whose effects depend on the current program state. It does not merely read data — it actively manipulates the execution cursor of the debugged process, which qualifies as Execute.

From the tool's definition Step backward one source line, stepping over function calls in reverse

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reverse_next Rate-limited

reverse_next 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": {
    "reverse_next": {
      "limits": [
        {
          "counter": "reverse_next_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 reverse_next

What does the reverse_next tool do? +

Step backward one source line, stepping over function calls in reverse. 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 reverse_next? +

Register the Rr MCP server in PolicyLayer and add a rule for reverse_next: 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 reverse_next? +

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

Can I rate-limit reverse_next? +

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

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

reverse_next 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.