gdb_continue · Gdb Multiarch MCP: Risk & Policy

WHAT IT DOES

What gdb_continue does on Gdb Multiarch

AI agents invoke gdb_continue to trigger actions in Gdb Multiarch. 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_continue needs a policy

This tool resumes execution of a debugged program, which is a direct execution control action. Misuse could cause the target process to run uncontrolled past intended breakpoints, execute unintended code paths, or trigger harmful operations in the debugged Nintendo Switch executable. It fits the Execute category as it triggers external program execution whose effects depend on the current program state and arguments.

From the tool's definition Continue execution until next breakpoint or completion

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gdb_continue Rate-limited

gdb_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": {
    "gdb_continue": {
      "limits": [
        {
          "counter": "gdb_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 Gdb Multiarch, so you can run agents against it safely.

FAQ

Questions about gdb_continue

What does the gdb_continue tool do? +

Continue execution until next breakpoint or completion. Only use when program is PAUSED. It is categorised as a Execute tool in the Gdb Multiarch 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_continue? +

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

What risk level is gdb_continue? +

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

Can I rate-limit gdb_continue? +

Yes. Add a rate_limit block to the gdb_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 gdb_continue completely? +

Set action: deny in the PolicyLayer policy for gdb_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 gdb_continue? +

gdb_continue is provided by the Gdb Multiarch MCP server (sbergeron42/gdb-multiarch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.