run_lldb · Xcode MCP: Risk & Policy

WHAT IT DOES

What run_lldb does on Xcode

AI agents invoke run_lldb to trigger actions in Xcode. 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 run_lldb needs a policy

Launching a debugger with optional arguments is a classic Execute action—it triggers an external operation (the LLDB process) whose effects depend on the arguments provided. An AI agent could use LLDB to run arbitrary code, inspect sensitive data, or alter the state of running applications. This has significant blast radius but falls short of Destructive (which requires irreversible data loss) or Financial.

From the tool's definition Tool name is 'run_lldb' and description states it 'Launches the LLDB debugger with optional arguments'. LLDB is a command-line debugger that can execute arbitrary code, evaluate expressions, and inspect/modify program state during debugging sessions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_lldb Rate-limited

run_lldb 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": {
    "run_lldb": {
      "limits": [
        {
          "counter": "run_lldb_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 Xcode, so you can run agents against it safely.

FAQ

Questions about run_lldb

What does the run_lldb tool do? +

Launches the LLDB debugger with optional arguments. It is categorised as a Execute tool in the Xcode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_lldb? +

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

What risk level is run_lldb? +

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

Can I rate-limit run_lldb? +

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

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

run_lldb is provided by the Xcode MCP server (xcode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.