reverse_finish · Rr MCP: Risk & Policy

WHAT IT DOES

What reverse_finish does on Rr

AI agents invoke reverse_finish 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_finish needs a policy

The tool executes a debugging operation that changes the execution state of a rr debugging session (reverse execution to function entry). While it does not create, modify, or destroy persistent data, it triggers an external operation (reverse debugging) whose effects depend on the current function context. This fits Execute category as it runs a debugger command that alters session state.

From the tool's definition Tool runs backward execution to a specific point ('Run backward to the point where the current function was called'). This is a command that triggers a debugger operation with side effects on session state and execution position.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reverse_finish Rate-limited

reverse_finish 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_finish": {
      "limits": [
        {
          "counter": "reverse_finish_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_finish

What does the reverse_finish tool do? +

Run backward to the point where the current function was called (function entry). 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_finish? +

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

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

Can I rate-limit reverse_finish? +

Yes. Add a rate_limit block to the reverse_finish 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_finish completely? +

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

reverse_finish 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.