将自然语言转化为强大的Perfetto痕迹分析

一个模型上下文协议（MCP）服务器，将自然语言提示转换为聚焦的Perfetto分析。快速解释故障、诊断ANR、发现CPU热线程、发现锁争用和内存泄漏——全部无需编写SQL。

✨ 特色

• 自然语言→SQL：用通俗易懂的英语提问，获得精确的Perfetto查询
• ANR检测：自动识别和分析应用程序无响应事件
• 性能分析：CPU配置、帧卡顿检测、内存泄漏检测
• 线程争用：查找同步瓶颈和锁争用
• 活页夹分析分析：分析IPC性能和系统交互缓慢

📋 先修条件

• Python 3.13+（macOS/自制）：

• uv（推荐）：

🚀 开始

光标

或者添加 ~/.cursor/mcp.json（全局）或.cursor/mcp.json（项目）：

克劳德密码

执行这个命令。更多信息请参见Claude代码MCP文档。

或者编辑 ~/claude.json（macOS）或%APPDATA%\Claude\claude.json（Windows）：

VS Code

或添加到.vscode/mcp.json（项目）中，或运行“MCP： Add Server”命令：

Perfetto MCP

Turn natural language into powerful Perfetto trace analysis

A Model Context Protocol (MCP) server that transforms natural-language prompts into focused Perfetto analyses. Quickly explain jank, diagnose ANRs, spot CPU hot threads, uncover lock contention, and find memory leaks – all without writing SQL.

✨ Features

• Natural Language → SQL: Ask questions in plain English, get precise Perfetto queries
• ANR Detection: Automatically identify and analyze Application Not Responding events
• Performance Analysis: CPU profiling, frame jank detection, memory leak detection
• Thread Contention: Find synchronization bottlenecks and lock contention
• Binder Profiling: Analyze IPC performance and slow system interactions

📋 Prerequisites

• Python 3.13+ (macOS/Homebrew):

  brew install [email protected]
  

• uv (recommended):

  brew install uv
  

🚀 Getting Started

Optional: Use a Local trace_processor_shell Binary

If your network environment blocks downloads, set PERFETTO_MCP_TRACE_PROCESSOR_BIN_PATH to an absolute path of a local trace_processor_shell binary.