xcrun_run_tool · Xctools MCP: Risk & Policy

WHAT IT DOES

What xcrun_run_tool does on Xctools

AI agents invoke xcrun_run_tool to trigger actions in Xctools. 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 xcrun_run_tool needs a policy

This tool directly executes external development tools via xcrun with potentially attacker-controlled arguments. While limited to the Xcode toolchain, an AI agent could use this to invoke compilers, build systems, or other tools in ways that modify the build environment, generate malicious artifacts, or access sensitive data.

From the tool's definition Tool description states 'Run a development tool via xcrun' — xcrun is a command-line utility that executes arbitrary Xcode tools with arguments supplied by the caller.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

xcrun_run_tool Rate-limited

xcrun_run_tool 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": {
    "xcrun_run_tool": {
      "limits": [
        {
          "counter": "xcrun_run_tool_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 Xctools, so you can run agents against it safely.

FAQ

Questions about xcrun_run_tool

What does the xcrun_run_tool tool do? +

Run a development tool via xcrun. It is categorised as a Execute tool in the Xctools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on xcrun_run_tool? +

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

What risk level is xcrun_run_tool? +

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

Can I rate-limit xcrun_run_tool? +

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

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

xcrun_run_tool is provided by the Xctools MCP server (nzrsky/xctools-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.