reverse_continue · Rr MCP: Risk & Policy

WHAT IT DOES

What reverse_continue does on Rr

AI agents invoke reverse_continue 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_continue needs a policy

This tool executes a debugging control operation (reverse continue) that drives program execution backwards in an rr replay session. While it doesn't delete data permanently, it triggers external process execution and changes session state in ways that depend on the current debugging context. Execute is the appropriate category as it runs/controls a process.

From the tool's definition 'Continue execution backward (rr' — triggers reverse execution in a debugging session, running the process in reverse which affects dynamic session state and program counter position

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reverse_continue Rate-limited

reverse_continue 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_continue": {
      "limits": [
        {
          "counter": "reverse_continue_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_continue

What does the reverse_continue tool do? +

Continue execution backward (rr. 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_continue? +

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

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

Can I rate-limit reverse_continue? +

Yes. Add a rate_limit block to the reverse_continue 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_continue completely? +

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

reverse_continue 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.