Führt Read-only Reverse Engineering von Electron-Apps, Binaries, Go/Rust, .NET und APKs mit TypeScript-Parsern und zitierbaren Fundstellen durch.
Auch bekannt als Firzus/agent-skills
- Stars
- 4
- Tools
- 8
- Downloads, 30 Tage
- —
- Neueste Version
- 0.1.0-alpha.2
- Letzter Commit
- 14. Nov. 2026
- Lizenz
- MIT
Was ist reverse-engineer MCP?
Führt Read-only Reverse Engineering von Electron-Apps, Binaries, Go/Rust, .NET und APKs mit TypeScript-Parsern und zitierbaren Fundstellen durch. Er stellt 8 Tools bereit, etwa triage, electron_surface, search.
Zusammenfassung generiert aus dem README des Projekts
Über reverse-engineer MCP server
Dieser Server ermöglicht es dir, kompilierten Code und Electron-Anwendungen direkt aus einem AI-Client heraus zu analysieren. Er bietet eine Read-only-Umgebung zur Inspektion von Binaries, Go- oder Rust-Builds, .NET-Assemblies und APK-Dateien mithilfe von TypeScript-basierten Parsern. Anstatt sich auf unzuverlässige Plattform-Befehle wie otool oder strings zu verlassen, nutzt er spezialisierte Tools, um kompakte, zitierte Antworten zu liefern, die spezifische Dateipfade, Zeilennummern oder Memory-Offsets enthalten.
Entwickler nutzen diesen Server, indem sie ihn in ihren Client-Einstellungen als MCP server via npx konfigurieren. Er benötigt Node.js 24.11 oder neuer und kann optional mit Ghidra, ilspycmd und jadx für fortgeschrittene Decompilation und Managed Code Analyse integriert werden. Um die Performance hochzuhalten, cached der Server Extraktionen und Analysen via SHA-256 und stellt sicher, dass alle Antworten unter dem Limit von 8 KB bleiben, wobei bei Bedarf Pfade zu größeren gecachten Dateien bereitgestellt werden. Dieser Ansatz erlaubt eine tiefgehende Inspektion von Electron IPC-Channels, asar-Integrität und Binary-Sections, ohne jemals den Zielcode auszuführen.
Was du damit machen kannst
- 1Triage von Binary-DateieigenschaftenIdentifiziere Architektur, Magic Bytes und Build-Marker einer verdächtigen Datei.
- 2Inspektion von Electron-App-InternalsUntersuche asar-Extraktionen, IPC-Channels und die von einer Electron-App verwendeten Node-Addon-Namen.
- 3Decompilation von Managed CodeFasse .NET- oder Android APK-Dateien zusammen und dekompiliere sie, um deren Typen und Funktionen zu verstehen.
- 4Suche in kompilierten AssetsFühre eine begrenzte Suche nach spezifischen Strings oder Patterns innerhalb eines Trees oder einer asar-Datei durch.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du reverse-engineer MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenreverse-engineer MCP in Claude Code installieren
$ claude mcp add reverse-engineer -- npx -y reverse-engineerreverse-engineer MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}reverse-engineer MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"reverse-engineer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}reverse-engineer MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"reverse-engineer","type":"stdio","command":"npx","args":["-y","reverse-engineer"]}'reverse-engineer MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}reverse-engineer MCP in Codex installieren
$ codex mcp add reverse-engineer -- npx -y reverse-engineerreverse-engineer MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.reverse-engineer] command = "npx" args = ["-y", "reverse-engineer"]
reverse-engineer MCP in Gemini CLI installieren
$ gemini mcp add -s user reverse-engineer npx -- -y reverse-engineerreverse-engineer MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"reverse-engineer": {
"command": "npx",
"args": [
"-y",
"reverse-engineer"
]
}
}
}reverse-engineer MCP tools 8
Erkannt aus dem READMEtriageelectron_surfacesearchreadbinary_inventorybuildinfodecompilemanaged
| triage | — | |
| electron_surface | — | |
| search | — | |
| read | — | |
| binary_inventory | — | |
| buildinfo | — | |
| decompile | — | |
| managed | — |
Automatisierte Checks
Geluften am 13. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)Bestanden
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSNicht geprüft
- Destruktive Tools sind markiertBestanden
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden
README
Auf GitHub ansehenreverse-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.
reverse-engineer MCP Fragen
Wie füge ich reverse-engineer MCP zu Claude Code hinzu?
Führe claude mcp add reverse-engineer -- npx -y reverse-engineer in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich reverse-engineer MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet reverse-engineer MCP?
Er stellt 8 Tools bereit, darunter triage, electron_surface, search, read, binary_inventory.
Kann der Server den Zielcode ausführen?
Nein, die Tools sind rein read-only und führen die Zieldateien niemals aus.
Wie geht der Server mit großen Ausgaben um?
Antworten werden standardmäßig kompakt gehalten (unter 8 KB); längere Ausgaben werden in einem Cache gespeichert und die Antwort liefert einen Pfad für das Paging.
Was passiert, wenn eine Binary fehlerhaft oder bösartig ist?
Der Server ist so konzipiert, dass er bei fehlerhaften oder bösartigen Binaries auf Teilresultate zurückfällt, anstatt hängen zu bleiben.