Realiza ingeniería inversa de solo lectura en aplicaciones Electron, binarios, Go/Rust, .NET y APKs mediante parsers en TypeScript y ubicaciones citables.
También conocido como Firzus/agent-skills
- Stars
- 4
- Herramientas
- 8
- Descargas, 30 días
- —
- Última versión
- 0.1.0-alpha.2
- Último commit
- 14 nov 2026
- Licencia
- MIT
¿Qué es reverse-engineer MCP?
Realiza ingeniería inversa de solo lectura en aplicaciones Electron, binarios, Go/Rust, .NET y APKs mediante parsers en TypeScript y ubicaciones citables. Expone 8 herramientas, como triage, electron_surface, search.
Resumen generado a partir del README del proyecto
Acerca del MCP server de reverse-engineer
Este servidor permite analizar código compilado y aplicaciones Electron directamente desde un cliente de IA. Proporciona un entorno de solo lectura para inspeccionar binarios, builds de Go o Rust, ensamblados .NET y archivos APK utilizando parsers basados en TypeScript. En lugar de depender de comandos de plataforma poco fiables como otool o strings, utiliza herramientas especializadas para ofrecer respuestas compactas y citadas que incluyen ubicaciones de archivos específicas, números de línea o desplazamientos de memoria.
Los desarrolladores utilizan este servidor configurándolo como un MCP server vía npx en los ajustes de su cliente. Requiere Node.js 24.11 o superior y puede integrarse opcionalmente con Ghidra, ilspycmd y jadx para descompilación avanzada y análisis de código gestionado. Para mantener el rendimiento, el servidor almacena en caché las extracciones y análisis mediante SHA-256 y garantiza que todas las respuestas se mantengan bajo un límite de 8 KB, proporcionando rutas a archivos en caché más grandes cuando es necesario. Este enfoque permite una inspección profunda de los canales IPC de Electron, la integridad de asar y las secciones de binarios sin ejecutar nunca el código objetivo.
Qué puedes hacer con él
- 1Triaje de propiedades de archivos binariosIdentifica la arquitectura, los magic bytes y los marcadores de compilación de un archivo sospechoso.
- 2Inspección de la estructura interna de aplicaciones ElectronExamina extracciones de asar, canales IPC y nombres de complementos de Node utilizados por una aplicación Electron.
- 3Descompilación de código gestionadoResume y descompila archivos .NET o Android APK para comprender sus tipos y funciones.
- 4Búsqueda en assets compiladosRealiza búsquedas delimitadas de strings o patrones específicos dentro de un árbol o un archivo asar.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar reverse-engineer MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar reverse-engineer MCP en Claude Code
$ claude mcp add reverse-engineer -- npx -y reverse-engineerInstalar reverse-engineer MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}Instalar reverse-engineer MCP en VS Code
.vscode/mcp.json
{
"servers": {
"reverse-engineer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}Instalar reverse-engineer MCP en VS Code CLI
$ code --add-mcp '{"name":"reverse-engineer","type":"stdio","command":"npx","args":["-y","reverse-engineer"]}'Instalar reverse-engineer MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}Instalar reverse-engineer MCP en Codex
$ codex mcp add reverse-engineer -- npx -y reverse-engineerInstalar reverse-engineer MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.reverse-engineer] command = "npx" args = ["-y", "reverse-engineer"]
Instalar reverse-engineer MCP en Gemini CLI
$ gemini mcp add -s user reverse-engineer npx -- -y reverse-engineerInstalar reverse-engineer MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}Herramientas de reverse-engineer MCP 8
Detectado desde el READMEtriageelectron_surfacesearchreadbinary_inventorybuildinfodecompilemanaged
| triage | — | |
| electron_surface | — | |
| search | — | |
| read | — | |
| binary_inventory | — | |
| buildinfo | — | |
| decompile | — | |
| managed | — |
Verificaciones automáticas
Ejecutado 13 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleAprobado
- Licencia de código abierto (OSI)Aprobado
- Commit o lanzamiento en el último añoAprobado
- El nombre del paquete no es similar a un paquete popularAprobado
- El endpoint remoto usa HTTPSNo verificado
- Las herramientas destructivas están etiquetadasAprobado
- Sin instrucciones ocultas para el modeloAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasAprobado
README
Ver en GitHubreverse-engineer server
The read-only MCP server and CLI behind the reverse-engineer skill. The skill is the agent-facing entry point; this server replaces the commands that are missing or fragile on a given platform (otool, strings, jq, go version -m, asar extraction) with TypeScript parsers, and answers in at most 8 KB with citable locations. Installing the skill does not install the server.
Tools
| Tool | What it returns |
|---|---|
triage |
Format by magic bytes, architecture, size, SHA-256, markers (Go, Rust, Electron fuses, N-API, packers) and the next call |
electron_surface |
Cached asar extraction, main, preloads and exposeInMainWorld keys, .node addons and the addon names called from JS, IPC channels grouped by call site (app wrappers included), fuses, asar integrity |
search |
Bounded search in a tree, a .asar or one file (hidden folders included), with file:line:col or file@offset and a short excerpt |
read |
Line ranges, a column window for minified code (instead of reformatting it), hexdumps |
binary_inventory |
PE, ELF and Mach-O sections, libraries and imports, exports, Node addon names, ASCII and UTF-16 strings, PE resources |
buildinfo |
Go build info (toolchain, main package, module, settings, dependencies) and Rust cargo-auditable packages |
decompile |
Ghidra headless, cached per file: list functions, map a string to the functions that use it, return one function's C |
managed |
.NET (via ilspycmd) and APK/DEX/JAR (via jadx): decompile once, summarize, return one type |
The catalog is about 6 KB for the 8 tools; the skill is about 5.5 KB.
Design rules:
- Compact by default. Each answer stays under
REVERSE_ENGINEER_MAX_BYTES(8192). Longer output is written to the cache, and the answer ends with its path, soreadandsearchcan page through it. - Cited facts. Every location is
file:line:col,file@0xoffset, a symbol or a string. - No blocking on common cases. A
.nodefile signed after packaging shows up as an unverified hash, not as an error. Malformed or hostile binaries degrade to partial results instead of hanging. - Read-only. The tools never run the target. They write only to their cache:
%LOCALAPPDATA%\reverse-engineer\cache,~/Library/Caches/reverse-engineer, or$XDG_CACHE_HOME/reverse-engineer(override withREVERSE_ENGINEER_CACHE). Exceptions: Ghidra refuses project paths with a dot folder, so with such a cache path (the Linux default~/.cache) its projects go to a private per-user folder in the temp directory; when the cache path contains a space, Ghidra keeps its settings in the home folder; jadx and the .NET SDK may write their own settings there on first use. - Cache by SHA-256. An extraction or an analysis is reused.
Use
Requirements: Node.js 24.11 or later. Optional: Ghidra 11+ with JDK 21 for decompile, ilspycmd (.NET 10 SDK) and jadx (JDK 21) for managed. The agent can install them with the skill's install guide: official releases go into a per-user tools root (%LOCALAPPDATA%\reverse-engineer\tools, ~/Library/Application Support/reverse-engineer/tools, or $XDG_DATA_HOME/reverse-engineer/tools; override with REVERSE_ENGINEER_TOOLS), without admin rights or a PATH change. The tools look there first, then on PATH, GHIDRA_INSTALL_DIR and the usual install folders.
The package is published to npm as an alpha prerelease, reverse-engineer, and listed in the MCP Registry as io.github.Firzus/reverse-engineer. Pin the exact version:
npx -y reverse-engineer@0.1.0-alpha.2 triage ./some.exe
npx -y reverse-engineer@0.1.0-alpha.2 electron_surface "C:\Program Files\App" --focus audio,microphone
Claude Code MCP configuration (project .mcp.json):
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": ["-y", "reverse-engineer@0.1.0-alpha.2", "mcp"]
}
}
}
On Windows, use "command": "cmd" with "args": ["/c", "npx", "-y", "reverse-engineer@0.1.0-alpha.2", "mcp"]. To run an unreleased build from a clone, run the Develop commands, then point the configuration at node <checkout>/mcp/reverse-engineer/dist/cli.mjs mcp.
Install the skill with npx skills add Firzus/agent-skills --skill reverse-engineer.
Develop
The toolchain is Vite+ (vite-plus, local dev dependency). .github/workflows/reverse-engineer-check.yml runs the same checks on Windows, macOS and Linux:
npm install
npx vp check # format, lint, type check
npx vp test # unit tests on synthetic and hostile fixtures
npx vp pack # bundle dist/cli.mjs, a single file with no runtime dependency
Tests against real targets are opt-in: set RE_TARGETS (a folder with app.asar, app.asar.unpacked/ and gh.exe), RE_NOTION_DIR (an installed Notion app), RE_GHIDRA=1, RE_DOTNET_DLL, or RE_APK.
Release
.github/workflows/reverse-engineer-publish.yml publishes to npm and the MCP Registry. Merging a version change to main publishes it, so treat the merge as the release decision. In the release pull request:
- Set the same version in
package.json,package-lock.json,server.json, the pinned commands above and in the skill'sSKILL.md; a unit test checks the first three. Whenvp packreports a new bundled dependency, add its license toTHIRD_PARTY_NOTICES.md. - Run the Develop checks, then
npm pack(it rebuildsdist/) and inspect the tarball:LICENSE,README.md,THIRD_PARTY_NOTICES.md,dist/cli.mjs,ghidra/ExportDecompiled.java,package.json.
The workflow stops when the version is already on npm and the MCP Registry. Otherwise it runs the check workflow, builds the tarball in a job without publishing rights, then publishes in the release environment, from a job that runs no project or dependency code. npm uses trusted publishing, with a prerelease published under its own dist-tag (alpha), never latest; the MCP Registry uses its GitHub OIDC login. A last job runs the published --version. When a run fails, fix the cause and use Re-run all jobs on that run: each publication step rechecks its registry and skips what already exists. Never overwrite or unpublish a version to hide a failed release; publish a new one.
npm must trust the workflow before the first automated release: in the reverse-engineer package settings, add a GitHub Actions trusted publisher with user Firzus, repository agent-skills, workflow reverse-engineer-publish.yml and environment release.
Benchmark
bench/ adapts the harness from leanrea to Windows and compares four arms: no skill, leanrea, REA (MCP and skill), and this tool. See bench/BENCHMARK.md for the method, the results and their limits.
License
MIT. The benchmark tasks and harness are adapted from leanrea, MIT-licensed; its notice is in bench/LICENSE-leanrea. Fuse names and the Go build-info layout follow the public formats documented by Electron and the Go toolchain; no code is copied from REA.
Preguntas sobre reverse-engineer MCP
¿Cómo agrego reverse-engineer MCP a Claude Code?
Ejecuta claude mcp add reverse-engineer -- npx -y reverse-engineer en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego reverse-engineer MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué herramientas proporciona reverse-engineer MCP?
Expone 8 herramientas, incluidas triage, electron_surface, search, read, binary_inventory.
¿Es el servidor capaz de ejecutar el código objetivo?
No, las herramientas son estrictamente de solo lectura y nunca ejecutan los archivos objetivo.
¿Cómo gestiona el servidor las salidas de gran tamaño?
Por defecto, las respuestas se mantienen compactas (menos de 8 KB); las salidas más largas se escriben en un caché y la respuesta proporciona una ruta para su paginación.
¿Qué ocurre si un binario está mal formado o es malicioso?
El servidor está diseñado para degradarse a resultados parciales en lugar de bloquearse cuando encuentra binarios mal formados o maliciosos.