gdb_run_control · Gdb MCP: Risk & Policy

WHAT IT DOES

What gdb_run_control does on Gdb

AI agents invoke gdb_run_control to trigger actions in Gdb. 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 gdb_run_control needs a policy

This tool directly executes and controls program execution within a debugger context. Commands like 'run', 'continue', 'step', and 'kill' trigger external code execution whose effects depend on the target program's behavior and arguments. While not inherently destructive (execution is reversible in principle), the execution of arbitrary debugged code qualifies it as Execute category.

From the tool's definition Tool description explicitly includes execution commands: "Run, continue, step, next, stepi, nexti, finish, until, interrupt, kill, or restart." These are GDB control flow operations that execute target processes and can trigger arbitrary program behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gdb_run_control Rate-limited

gdb_run_control 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": {
    "gdb_run_control": {
      "limits": [
        {
          "counter": "gdb_run_control_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, so you can run agents against it safely.

FAQ

Questions about gdb_run_control

What does the gdb_run_control tool do? +

Run, continue, step, next, stepi, nexti, finish, until, interrupt, kill, or restart. It is categorised as a Execute tool in the Gdb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gdb_run_control? +

Register the Gdb MCP server in PolicyLayer and add a rule for gdb_run_control: 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. Nothing to install.

What risk level is gdb_run_control? +

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

Can I rate-limit gdb_run_control? +

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

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

gdb_run_control is provided by the Gdb MCP server (traver88/gdb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.