今日热榜中文
← Back to plugins

Tool connections (MCP)

REA — Reverse Engineer Anything

morluto/rea

Let AI investigate how an application's features work and return code and runtime evidence you can check.

Introduction

Prepared by 今日热榜 from public project documentation

REA connects application and file analysis tools to an AI assistant when you want to understand a shipped feature without a complete source tree. It supplies MCP, a CLI, and the reverse-engineer-anything skill, with workflows for JavaScript, Electron, native programs, and runtime behavior. The skill provides investigation instructions; actual analysis requires the REA tools and any runtime or analysis engine needed for the target. Use it for software you own or are authorized to examine. REA-authored code is MIT-licensed; external tools such as Hopper and IDA have their own licenses and costs.

Get started

Check the requirements, then choose your AI assistant to see the setup steps.

What you need
  • Node.js 22.x at least 22.19, 24.x at least 24.11, or 26+, and npm.
  • Static and native analysis have different requirements; prepare Hopper, Ghidra, or IDA when the target needs one.
Costs
REA-authored code is MIT-licensed; external analysis engines have their own licenses, some commercial, and assistant usage is separate.
Required permissions
Setup changes selected MCP and skill configurations with backups. Static inspection reads files; runtime capture can launch or interact with target applications. The assistant’s model provider also receives the tool results it uses.
CodexOfficial setup documented

The official setup lists Codex; full setup registers MCP and installs the matching investigation skill.

Setup steps

  1. Check Node.js, npm, and the required analysis tools using the installation guide.
  2. Follow the documented REA setup, select Codex, and review proposed configuration changes before approving them.
  3. Restart the assistant and check readiness for the task; installing only the skill does not connect the analysis tools.

Check that setup worked

Use a small JavaScript application you are authorized to inspect and ask for module relationships and evidence; avoid launching native targets or installing engines for this check.

Official sources

Claude CodeOfficial setup documented

The official setup lists Claude Code; full setup registers MCP and installs the matching investigation skill.

Setup steps

  1. Check Node.js, npm, and the required analysis tools using the installation guide.
  2. Follow the documented REA setup, select Claude Code, and review proposed configuration changes before approving them.
  3. Restart the assistant and check readiness for the task; installing only the skill does not connect the analysis tools.

Check that setup worked

Use a small JavaScript application you are authorized to inspect and ask for module relationships and evidence; avoid launching native targets or installing engines for this check.

Official sources

CursorOfficial setup documented

The official setup lists Cursor; full setup registers MCP and installs the matching investigation skill.

Setup steps

  1. Check Node.js, npm, and the required analysis tools using the installation guide.
  2. Follow the documented REA setup, select Cursor, and review proposed configuration changes before approving them.
  3. Restart the assistant and check readiness for the task; installing only the skill does not connect the analysis tools.

Check that setup worked

Use a small JavaScript application you are authorized to inspect and ask for module relationships and evidence; avoid launching native targets or installing engines for this check.

Official sources

Official sources

Setup guidance reviewed 2026-10-13 · Based on public documentation; not individually installed and tested here.

Ways to use it

  • Inspect modules and relationships in JavaScript and Electron applications
  • Connect analysis engines to examine native programs and runtime behavior
  • Use an investigation skill to record evidence and limitations

The project’s original description

Reverse engineer anything with agents, from app behavior down to native binaries.

More projects of this type

These other listed projects can help you compare use cases and setup requirements.

  • MarkItDown MCP — Let AI convert PDF, Word, and spreadsheet files into text it can work with.
  • Context7 — Give AI current library documentation and examples before it writes code.
  • Chrome DevTools MCP — Let AI inspect Chrome pages to investigate errors and loading performance.

Sources and ranking

This directory lists AI development plugins with public source code and a clear purpose. Browse by task, then open an introduction to learn what a project does, who it is for, and what you need to get started. It covers selected projects, not every AI plugin.

How do the three plugin types differ?

Tool connections (MCP) let AI assistants use external tools such as browsers, code repositories and databases. MCP is the protocol used for these connections.

Reusable skills give a compatible AI assistant instructions and guidance for a particular task.

Editor plugins run inside the software you use to write code, adding AI chat, completions or suggested edits.

How does “Most starred” work?

Projects are sorted by their total GitHub stars. Stars indicate interest; they are not downloads, active users or quality scores. A skill pack counts as one project. Daily star growth is not shown without historical records.

What does “Recently updated” mean?

It uses the most recent code push, which may not be a new release. The 7-day filter checks that project update time; ranking still uses all-time stars. Each introduction shows when its star count was collected. Failed updates keep the last saved data.

Introductions are based on public project documentation. These projects have not each been installed and tested here. Check the project documentation for setup, compatibility and service costs. Refreshing this list only reads saved data; it does not start collection.

UTC+8