Mouseww/anything-analyzer

全能协议分析工具：浏览器抓包 + MITM 代理 + 指纹伪装 + AI 分析 + MCP Server 无缝对接 AI Agent/IDE | All-in-one protocol analysis toolkit — built-in browser capture, MITM proxy, JS hooks, fingerprint spoofing, AI analysis & MCP server for agent integration

What it solves

Anything Analyzer is a comprehensive network traffic capture tool that uses AI to automate the reverse engineering of protocols and APIs. It replaces the fragmented experience of using multiple tools (like DevTools, Fiddler, or Wireshark) by providing a unified session for traffic from various sources and using LLMs to analyze the captured data.

How it works

The tool employs a dual-channel capture system:

  • Embedded Browser: Uses the Chrome DevTools Protocol (CDP) to intercept requests and responses directly from a built-in browser.
  • MITM Proxy: An integrated HTTPS Man-in-the-Middle proxy (port 8888) that captures traffic from desktop apps, terminal commands (curl/wget), scripts (Python/Node.js), and mobile devices/IoT via Wi-Fi proxy settings.

Captured traffic is aggregated into a single session. The AI analysis pipeline then performs a two-phase process: first filtering out noise requests and then conducting deep analysis based on one of five modes (Automatic, API Reverse Engineering, Security Audit, Performance Analysis, or JS Encryption Reverse Engineering).

Who it’s for

  • Reverse Engineers: Those looking to document API endpoints, authentication flows, and recreate requests in Python.
  • Security Auditors: Users auditing for token leaks, CSRF/XSS vulnerabilities, and sensitive data exposure.
  • Developers: Developers debugging CLI tools, microservices, or mobile app protocols.

Highlights

  • Multi-Source Capture: Unified capture from browsers, desktop apps, terminal, scripts, and mobile devices.
  • AI-Driven Analysis: Two-phase analysis to filter noise and generate reports on protocol reverse engineering or security audits.
  • JS Hooking: Automatically intercepts encryption calls (e.g., crypto.subtle, CryptoJS) and extracts encryption code from JS files.
  • AI Agent Integration: Includes an MCP Client and built-in MCP Server to allow AI agents like Claude Desktop or Cursor to use the capture and analysis capabilities.
  • Cross-Platform Support: Available for Windows, macOS, and Linux.

Related

  • Project
    chrisryugj/Docufinder

    Anything is a Windows/macOS desktop app that locally indexes the full text of many document types (including Korean HWP files) and lets you search by keyword, file name, or natural‑language question. It offers AI‑powered Q&A and summarisation (via Gemini or OpenAI‑compatible APIs) but can run completely offline. Built with React/Tauri, it uses SQLite FTS5 for keyword search and ONNX‑based Korean embeddings for semantic search, plus OCR for images. A special “Lite” build removes all network code for highly secure environments.

  • Project
    HKUDS/CLI-Anything

    CLI‑Anything is an open‑source Python framework that automatically generates agent‑friendly command‑line wrappers for any software. It ships a package manager (`cli‑anything‑hub`) that indexes dozens of community‑built CLIs (GIMP, Blender, Zoom, GIS tools, etc.) and lets agents discover, install, and invoke them via structured JSON output. Developers can use a 7‑phase generator to create new CLIs for any application, and AI agents (Claude Code, Cursor, Pi, OpenClaw, …) can install the meta‑skill to browse the registry autonomously. The project is actively maintained, well‑tested (2 461 passing tests), and Apache‑2.0 licensed.

  • Project
    appium/appium-mcp

    An MCP server that enables AI assistants to automate mobile apps on iOS and Android using natural language and vision-based element finding.

  • Project
    zhizhuodemao/js-reverse-mcp

    js‑reverse‑mcp is a Node.js MCP server that lets LLM agents debug and reverse‑engineer JavaScript in Chrome. It wraps DevTools data (scripts, breakpoints, network, WebSocket, storage) into 24 concise tools designed for AI‑driven reasoning, and includes optional stealth layers (Patchright fork and CloakBrowser) for anti‑bot sites.

  • Project
    CyberStrikeus/CyberStrike

    CyberStrike is an open‑source AI agent that turns any LLM (Claude, GPT, Gemini, etc.) into an autonomous penetration‑testing platform. It adds a security‑focused “intelligence layer”, ships 13+ specialised agents and 7,600+ signed security‑skill files, supports 150+ AI providers (including offline models), and can orchestrate real tools locally or on remote Bolt servers. A TUI, optional web UI, and built‑in HackBrowser complete the workflow.