watch · gdb and rr Debugging MCP: Risk & Policy

WHAT IT DOES

What watch does on gdb and rr Debugging

AI agents invoke watch 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 watch needs a policy

A watchpoint modifies the debugger's state by registering a hardware/software breakpoint that triggers on memory or variable changes. This is not a pure read — it actively alters the debugging session's execution behavior. It falls under Execute as it configures and affects program execution flow in the debugger, though it doesn't run arbitrary code or delete data.

From the tool's definition Set a watchpoint that stops when an expression changes

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watch Rate-limited

watch 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": {
    "watch": {
      "limits": [
        {
          "counter": "watch_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 watch

What does the watch tool do? +

Set a watchpoint that stops when an expression changes. 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 watch? +

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

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

Can I rate-limit watch? +

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

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

watch 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.