continue_exec · gdb and rr Debugging MCP: Risk & Policy

WHAT IT DOES

What continue_exec does on gdb and rr Debugging

AI agents invoke continue_exec 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 continue_exec needs a policy

This tool resumes execution of a debugged program, which is an Execute-class action—it triggers an external operation (program continuation) whose effects depend on the program's internal state and code. While debugging tools are typically safe in isolated environments, misuse by an AI agent could cause unintended program behavior, crashes, or resource exhaustion.

From the tool's definition Tool name 'continue_exec' and description 'Continue execution' indicates the tool runs/resumes program execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

continue_exec Rate-limited

continue_exec 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": {
    "continue_exec": {
      "limits": [
        {
          "counter": "continue_exec_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 continue_exec

What does the continue_exec tool do? +

Continue execution. Blocks until next stop. 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 continue_exec? +

Register the gdb and rr Debugging MCP server in PolicyLayer and add a rule for continue_exec: 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 continue_exec? +

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

Can I rate-limit continue_exec? +

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

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

continue_exec 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.