What is instruments-mcp-server CLAUDE.md?

An MCP server for Apple’s Xcode Instruments, a performance-analysis tool for iPhone, iPad, and Mac applications. It collects trace data and turns it into structured results with severity labels and summaries.

Use it to profile apps, inspect raw traces, analyze performance data, compare results with a baseline, and examine memory, launch time, networking, energy, or SwiftUI behavior.

It reduces the manual work of reading performance traces and makes problems such as slow code, memory leaks, hangs, or high energy use easier to identify.

How nemanjavlahovic/instruments-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nemanjavlahovic/instruments-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nemanjavlahovic/instruments-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nemanjavlahovic/instruments-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nemanjavlahovic/instruments-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/nemanjavlahovic/instruments-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nemanjavlahovic/instruments-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/nemanjavlahovic/instruments-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nemanjavlahovic/instruments-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/nemanjavlahovic/instruments-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 480 This file is loaded in full into every session.

When invoked 480 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00480	$0.00480
Opus 5.5	$0.00192	$0.00192
Sonnet 5.5	$0.00096	$0.00096
Haiku 4.5	$0.00048	$0.00048

Measured 2mo ago against content hash 326b21165e76, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

instruments-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 37 lines

What it actually says

InstrumentsMCP

What This Is

AI-native performance profiling for iOS and macOS apps. Wraps Xcode Instruments (xctrace CLI) as an MCP server, parsing trace data into structured JSON with severity classifications and actionable summaries.

Architecture

src/index.ts - MCP server entry point, registers all tools
src/tools/ - Tool definitions (profile, list, analyze, baseline)
src/parsers/ - Template-specific XML→JSON parsers (time-profiler, swiftui, allocations, hangs, app-launch, energy, leaks, network)
src/utils/xctrace.ts - Low-level xctrace CLI wrapper
src/utils/xml.ts - XML parsing with fast-xml-parser

Key Design Decisions

Each Instruments template has its own parser with domain-specific heuristics
Severity classification (ok/warning/critical) uses tuned thresholds per metric type
The profile_raw + analyze_trace combo handles any template without a dedicated parser
Traces are stored in ~/.instruments-mcp/traces/ with timestamps

Adding New Parsers

Create src/parsers/<template-name>.ts
Export a parse function that takes TOC XML + table XML and returns structured data
Add a dedicated profile_<name> tool in src/tools/profile.ts
Include severity classification and a text summary

xctrace Compatibility

xctrace 26+ uses Deferred recording mode by default — time-profile table may be empty
profile_cpu and performance_audit fall back to time-sample table automatically
xctraceExport retries up to 5 times for intermittent "Document Missing Template Error"
XML parser isArray config wraps node, row, frame, backtrace etc. in arrays — always unwrap [0]
xctrace 26 backtrace frames use @_name for function names and nested binary.@_name for module

Tech Stack

TypeScript, Node.js >= 20, ESM modules
@modelcontextprotocol/sdk for MCP protocol
fast-xml-parser for XML→JS conversion
zod for tool parameter schemas

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 37 lines · 480 tokens per session scan A 326b21165e76

Subscribe to this mod's changes

instruments-mcp-server CLAUDE.md is an instructions file published in the GitHub repository nemanjavlahovic/instruments-mcp-server (20 stars, last pushed 1mo ago), licensed MIT. It adds 480 tokens to every session, about $0.0019 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

instruments ios macos mcp mcp-server performance

instruments-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
instruments-mcp-server CLAUDE.mdnemanjavlahovic/instruments-mcp-server	Instructions file	20	1mo ago	MIT	A	480	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

instruments-mcp-server: Instructions file for Claude Code