Quick Start
Requirements: macOS, Xcode, Node.js >= 20
Add to your project's .mcp.json:
{
"mcpServers": {
"instruments": {
"command": "npx",
"args": ["-y", "instrumentsmcp@latest"]
}
}
}
Or run directly:
接入你的智能体
从发布者处安装。不是 PlugMCP 端点。
远程 URL 还是本机命令? 两种安装方式的区别
来自发布者
Requirements: macOS, Xcode, Node.js >= 20
Add to your project's .mcp.json:
{
"mcpServers": {
"instruments": {
"command": "npx",
"args": ["-y", "instrumentsmcp@latest"]
}
}
}
Or run directly:
MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, SwiftUI, memory, hitches) instead of raw xctrace XML
npx instrumentsmcp@latestWorks with Claude Code, Cursor, Windsurf, and any MCP client.
Ask your agent to profile. It records a trace, drives the simulator, and returns structured results:
=== Time Profiler === severity: [WARNING] samples: 1587
Hotspots:
UpdateStack::update() (AttributeGraph) 42.3ms self ━━━━━━╌╌╌╌╌╌╌╌╌ 12.1%
FeedViewModel.loadItems() (MyApp) 28.1ms self ━━━━╌╌╌╌╌╌╌╌╌╌╌ 8.0%
Main thread blockers:
[WARNING] FeedViewModel.loadItems() 28.1ms
35 tools across profiling, UI automation, simulator control, and trace analysis. Full tool list →
profile_cpu, profile_swiftui, profile_memory, profile_hitches, profile_launch, profile_energy, profile_leaks, profile_networkprofile_scenario records a trace while executing UI steps (tap, scroll, type, launch)start_profiling / stop_profiling for manual interactionperformance_audit runs 5 templates and combines the resultsprofile_raw handles templates without a dedicated parserDrive the simulator programmatically: ui_tap, ui_type, ui_swipe, ui_gesture, ui_snapshot, ui_long_press. Powered by AXe CLI (brew tap cameroncooke/axe && brew install axe).
Launch/terminate apps, open deep links, push notifications, take screenshots, set location, toggle dark mode.
Re-analyze saved traces, drill into specific functions, track regressions with baselines, generate Markdown reports.
Record traces from the terminal without an MCP client:
npx instrumentsmcp record --process MyApp
npx instrumentsmcp record --process MyApp --template Allocations
Ctrl+C to stop. Feed the trace to your agent for analysis.
booted, device name, UDID) resolved automaticallysrc/
├── index.ts # MCP server entry + CLI router
├── cli.ts # CLI mode (instrumentsmcp record)
├── tools/
│ ├── profile.ts # One-shot profiling tools
│ ├── simulator.ts # Simulator control + start/stop + scenarios
│ ├── analyze.ts # Trace analysis + symbolication + audit
│ ├── baseline.ts # Baseline comparison + report generation
│ ├── investigate.ts # Drill-down + trace listing
│ ├── ui.ts # UI automation (snapshot, tap, type, swipe)
│ └── list.ts # Discovery tools (status, templates, devices)
├── parsers/ # Template-specific XML→JSON parsers
└── utils/ # xctrace, simctl, AXe wrappers + shared helpers
git clone https://github.com/nemanjavlahovic/instruments-mcp-server.git
cd instruments-mcp-server
npm install && npm run build
Point your MCP client to dist/index.js.
MIT
MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, SwiftUI, memory, hitches) instead of raw xctrace XML
工具
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
常见问题
在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
此记录未列出必需的环境变量。
Instruments 通过 stdio 在本地运行。
上次检查时间:2026-10-27。 MCP server for Xcode Instruments — AI agents get structured performance profiling (CPU, SwiftUI, memory, hitches) instead of raw xctrace XML