rr_record · gdb and rr Debugging MCP: Risk & Policy

WHAT IT DOES

What rr_record does on gdb and rr Debugging

AI agents invoke rr_record to trigger actions in gdb and rr Debugging. 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 rr_record needs a policy

The tool executes and instruments a program to capture its execution trace. While not destructive in itself, it triggers external operations (recording system calls, memory state, execution flow) that cannot be trivially undone and whose side effects depend on the program being recorded.

From the tool's definition Tool name 'rr_record' is part of the rr reverse debugging suite; rr (Mozilla's rr) records program execution traces for replay.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rr_record Rate-limited

rr_record 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": {
    "rr_record": {
      "limits": [
        {
          "counter": "rr_record_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 gdb and rr Debugging, so you can run agents against it safely.

FAQ

Questions about rr_record

What does the rr_record tool do? +

rr_record. It is categorised as a Execute tool in the gdb and rr Debugging MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on rr_record? +

Register the gdb and rr Debugging MCP server in PolicyLayer and add a rule for rr_record: 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 gdb and rr Debugging. Nothing to install.

What risk level is rr_record? +

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

Can I rate-limit rr_record? +

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

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

rr_record is provided by the gdb and rr Debugging MCP server (schuay/gdb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.