Record one explicit Instruments template. Use this when the user names a template such as Leaks or Allocations; for broad hangs/CPU profiling prefer the bundled skill or profile_running_app.
AI agents invoke track_running_app to trigger actions in XcodeTraceMCP. 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.
Recording an Instruments trace involves launching and controlling an external profiling process (xctrace) against a running application. This is an Execute-category action because it triggers an external operation whose effects depend on the arguments (which template, which app). It is not merely reading existing data — it actively starts a recording session.
From the tool's definition "Record one explicit Instruments template" — the tool actively records/runs an Instruments profiling session against a running app, triggering an external operation.
Documented attack patterns abuse exactly the kind of access track_running_app gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and XcodeTraceMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for track_running_app:
{
"version": "1",
"default": "deny",
"tools": {
"track_running_app": {
"limits": [
{
"counter": "track_running_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}track_running_app 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.
Free to start. No card required.
Record one explicit Instruments template. Use this when the user names a template such as Leaks or Allocations; for broad hangs/CPU profiling prefer the bundled skill or profile_running_app. It is categorised as a Execute tool in the XcodeTraceMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the XcodeTrace MCP server in PolicyLayer and add a rule for track_running_app: 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 XcodeTraceMCP. Nothing to install.
track_running_app is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the track_running_app 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.
Set action: deny in the PolicyLayer policy for track_running_app. 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.
track_running_app is provided by the XcodeTrace MCP server (jamesrochabrun/xcodetracemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from XcodeTraceMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 XcodeTraceMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.