finish · gdb and rr Debugging MCP: Risk & Policy

WHAT IT DOES

What finish does on gdb and rr Debugging

AI agents invoke finish 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 finish needs a policy

The 'finish' command resumes program execution until the current function returns. While debugging tools themselves are not inherently malicious, this tool directly controls program execution flow. An AI agent could misuse it to execute arbitrary attacker-controlled code by manipulating the target program or its context.

From the tool's definition "Run until current function returns" indicates execution control of a debugger that continues a suspended program.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

finish Rate-limited

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

FAQ

Questions about finish

What does the finish tool do? +

Run until current function returns. Blocks until stopped. 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 finish? +

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

What risk level is finish? +

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

Can I rate-limit finish? +

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

Set action: deny in the PolicyLayer policy for 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 finish? +

finish 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.