Skip to content
KitploitKITPLOIT
أدواتعمليات الاستغلالالمدونة
Log in
إرسال
أدواتعمليات الاستغلالالمدونة
إرسال

أدوات الاختراق واختبار الاختراق والأمن السيبراني لترسانتك الأمنية!

Kitploit هو دليل لأدوات الاختراق والأمن السيبراني واختبار الاختراق. اكتشف آخر تحديثات المشاريع للعثور على الثغرات وتحليل الأنظمة وأتمتة الاختبارات وتعزيز أمنك.

الخلاصاتاتصالالخصوصية© 2026 Kitploit

دليل الأدوات

الفئات

عرض جميع الفئات
Loading categories
mcp-reverse — MCP server exposing 180+ reverse-engineering tools that aggregate Ghidra, IDA, x64dbg, Frida and 56 other backends with native binary parsers and a 4,200-skill knowledge base. | Kitploit
أدوات/GitHubGitHub/1llu50ry/mcp-reverse
Dynamic Analysis (Sandboxing)Exploit FrameworksReverse EngineeringDebuggersMalware AnalysisCTFMobile SecurityBinary AnalysisLearning & EducationAI-Assisted ReversingCurated ResourcesFirmware Analysis
590108822منذ 7س 27دتمت المراجعة من قبل Kitploit
مشاركة
GitHub1llu50ry/mcp-reverse

mcp-reverse

MCP server exposing 180+ reverse-engineering tools that aggregate Ghidra, IDA, x64dbg, Frida and 56 other backends with native binary parsers and a 4,200-skill knowledge base.

عرض المستودع
المحتوى غير متوفر باللغة المطلوبة. عرض النسخة الإنجليزية.
<div align="center">

# 🎮 decompile

### One MCP for reverse engineering across binaries, applications, and runtime behavior.

**230+ MCP tools · 60+ RE/debug backends · 9 host-side plugins · 6,000+ skills · 170+ agents · 160+ subagents · 190+ plugins · 3,000+ prompts · multi-agent mesh · native x86-64 + ARM64 emulators**

[![version](https://img.shields.io/badge/version-0.0.1-blue)](CHANGELOG.md) [![tests](https://img.shields.io/badge/tests-133/133-success)](tests/) [![tools](https://img.shields.io/badge/MCP%20tools-230+-blue)](src/) [![backends](https://img.shields.io/badge/RE%20backends-60+-blueviolet)](src/retools.ts) [![skills](https://img.shields.io/badge/skills-6,000+-orange)](db/skills.db) [![docker](https://img.shields.io/badge/docker-multi--arch-informational)](Dockerfile) [![license](https://img.shields.io/badge/license-MIT-green)](LICENSE) [![audit](https://img.shields.io/badge/npm%20audit-0-brightgreen)](package.json)

> **v5.0.0 released.** 19 GiB → 3.3 GiB working tree (83% smaller via gzipped source archives), + four feature waves: host plugin build systems, Frida bridge + dynamic analysis, ARM64 emulator + decompile cache + chunking, bindiff / ROP / game-engine metadata / MCP sampling / SVG visualization. See [CHANGELOG](https://github.com/1llu50ry/mcp-reverse/blob/main/CHANGELOG.md).

[Quickstart](#30-second-quickstart) · [Architecture](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/architecture.md) · [Comparison](#comparison) · [Agent Mesh](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/agent-mesh.md) · [MCP Hub](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/mcp-hub.md) · [Ethics](#ethics--responsible-use)

[English](https://github.com/1llu50ry/mcp-reverse/blob/main/README.md) · [Русский](https://github.com/1llu50ry/mcp-reverse/blob/main/README-ru.md) · [简体中文](https://github.com/1llu50ry/mcp-reverse/blob/main/README-zh.md)

</div>

---

## Why this exists

Reverse engineering a modern application involves five static tools (Ghidra, IDA, Binary Ninja, radare2, Hopper), three debuggers (x64dbg, WinDbg, GDB/LLDB), a hex-editor, a memory scanner, an instrumentation framework, and a stack of format parsers (PE, ELF, Mach-O, DEX, Minidump, WASM, .NET, ASAR, GGUF, BEAM, Go). Switching between them costs hours. Teaching a model to drive even one of them well costs more.

**This server:**

1. **Aggregates 60+ RE / debug MCP backends** behind one connection — `smart_decompile` picks IDA when running, falls back to Ghidra, then Binary Ninja, then radare2.
2. **Ships 230+ native MCP tools** so most answers don't need an external backend at all — PE / ELF / Mach-O / DEX / WASM / Minidump / ZIP / .NET / IL2CPP / ASAR / GGUF / BEAM / Go buildinfo parsers, AoB signature scan, Shannon entropy, crypto-constant identification, PDB70 → Microsoft symbol server URL, PyInstaller TOC, HAR summary, SQLite inspect, ELF notes, Apple IPS.
3. **Lets agents collaborate** through a shared mesh — DM, channels, task handoff, adversarial voting, shared KV knowledge-base, named locks for coordination. Zero-dep JSON persistence.
4. **Curates 6,000+ skills, 170+ agents, 160+ subagents, 190+ plugins, 3,000+ prompts** — hand-written deep references plus imported open-source techniques, full-text searchable.
5. **Ships a one-shot CLI** (`decompile setup`, `decompile analyze <path>`, `decompile capabilities`, `decompile doctor`) that registers the MCP with Claude Code / Cursor / Codex / Windsurf / Gemini and returns structured findings with evidence and unknowns.

If you're on security-research, binary-analysis, defensive-engineering, or SDK work — this collapses a day of tool-shuffling into one MCP connection.

## 30-second quickstart

[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/1llu50ry/decompile?quickstart=1)

### Install — one command, everything

Needs **Node.js 24+** for the MCP server ([how to get it](https://github.com/1llu50ry/Decompile/wiki/Installation#1-prepare-your-computer)). Pick **one**:

```bash
# Linux / macOS / FreeBSD / Termux
curl -fsSL https://raw.githubusercontent.com/1llu50ry/Decompile/main/install.sh | sh
```

```powershell
# Windows (PowerShell)
irm https://raw.githubusercontent.com/1llu50ry/Decompile/main/install.ps1 | iex
```

```bash
# npx (any OS, nothing kept but the RE tools)
npx -y decompile@latest setup -i --npx
```

Each one installs **everything** and wires it up:

- the decompile server + CLI (16 platform bundles, SHA-256 verified) and agent registration (`setup -i`, 42 agents);
- **RE programs** into `~/.decompile/tools` (~1.5 GB): Ghidra + Java 21, radare2, UPX, x64dbg (Windows),
  FakePDB, and a Python env with frida, angr, capstone, keystone, unicorn, lief, r2pipe, pyghidra,
  volatility3, yara, mitmproxy, ROPgadget — then `env.json` hooks them into the server;
- our bridge plugins into IDA / Binary Ninja / Cheat Engine **when those are installed** (they are commercial, so not downloaded).

`--minimal` (`-Minimal` on Windows) installs only the core; add the RE programs later with
`decompile retools install`. Other flags: `--dry-run`, `--version v0.0.1`, `--method npm|npx`,
`--install-node`, `--no-setup`, `--uninstall` — see the [Installation wiki](https://github.com/1llu50ry/Decompile/wiki/Installation).
Check the result with `decompile doctor`; manage RE programs with `decompile retools status | install | env`.

### The npx one-liner (nothing installed)

```bash
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup
```

By default it configures Claude Code. Pass `-i` for an interactive
picker over 42 supported agents (Claude Code / Desktop, Codex, Cursor,
VS Code, Zed, Windsurf, Gemini CLI, Grok Build, Qwen Code, Kimi,
DeepSeek Harness, LM Studio, Cline in every host, Copilot CLI, Goose,
and 25+ more). The workflow-instructions skill is installed alongside
the registration. Restart your agent and you're done.

Variations:

```bash
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup -i                           # interactive picker (42 agents)
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup --all-detected               # every detected agent
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup --client claude_code         # one specific client
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup --client codex --client cursor --client dsh
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup --dry-run                    # preview without writing
npx -y https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz setup --npx                        # cache-safe (npx-based) registration
npm install -g https://github.com/1llu50ry/Decompile/releases/latest/download/decompile.tgz && decompile --help               # install the command permanently
```

### Other entry points

```bash
# clone + build (local dev)
git clone https://github.com/1llu50ry/decompile && cd decompile
npm install && npx tsc
npm test # 20/20 should pass

# run the MCP server over HTTP (Docker-friendly)
docker compose up

# drive it from the CLI (no MCP client needed)
decompile analyze path/to/binary       # structured findings JSON
decompile capabilities                 # list every tool + skill
decompile doctor                       # runtime + DB + registrations
decompile providers                    # list configured RE backends
decompile guidance                     # print the workflow instructions
```

### Ask the agent

```text
Understand how feature X works in that app, show me the evidence,
and port it to my project.
```

Replace `X` and `that app` with your actual target; the server returns
structured findings with evidence tool-backed and unknowns called out.

Point your MCP client at it, then ask any of:

- *"Analyze `C:\game\binary.exe` and tell me what packer it uses."* → calls `analyze_binary` (entropy + Rich Header + Debug Directory + imports + crypto constants)
- *"Decompile `0x401000` using every connected backend and spot disagreements."* → `hub_consensus_call matcher=decompile`
- *"Alice, hand off driver.sys unpacking to Bob; Cursor review the result."* → mesh orchestration
- *"BM25 search 'battleye shellcode detection'."* → `bm25_search` ranks 4,230 docs by BM25 relevance

## Architecture

```mermaid
flowchart LR
 subgraph clients[" MCP clients "]
 C1[Claude Code]
 C2[Codex / ChatGPT]
 C3[Cursor]
 C4[Copilot CLI]
 C5[custom]
 end

 subgraph server[" decompile (this repo) "]
 direction TB
 T[230+ MCP tools]
 M[Agent Mesh<br/>DM · channels · tasks · votes · KB · locks]
 H[MCP Hub<br/>smart_decompile · consensus_call]
 N[Native parsers<br/>PE · ELF · Mach-O · DEX · WASM · Minidump · ZIP · .NET · ASAR · GGUF · BEAM · Go]
 S[Skill library<br/>6,000+ docs · BM25]
 end

 subgraph backends[" 60+ RE / debug MCP backends "]
 B1[Ghidra · IDA · Binja]
 B2[x64dbg · WinDbg · GDB · LLDB]
 B3[Cheat Engine · Frida]
 B4[PCILeech · Memflow]
 B5[Volatility · YARA · angr]
 end

 C1 & C2 & C3 & C4 & C5 -->|stdio or HTTP| server
 server -->|hub_connect| B1 & B2 & B3 & B4 & B5
```

## Verticals

The game-hacking framing is historical — the tooling covers every RE discipline:

| Vertical | Why this project fits | Docs |
|---|---|---|
| 🎮 **Game security + anti-cheat** | 6,000+ hand-written + imported skills across every major anti-cheat and engine family. | this README |
| 🦠 **Malware analysis** | PE / minidump / Rich Header / Debug Directory parsers + 60+ backend hub (YARA, Volatility, angr, Qiling). | [docs/verticals/malware-analysis.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/verticals/malware-analysis.md) |
| 📱 **Mobile security (iOS + Android)** | Mach-O (fat + arm64e) + DEX + APK parsers + Hopper + Frida + JADX + Magisk + idevice MCPs. | [docs/verticals/mobile-security.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/verticals/mobile-security.md) |
| 🔧 **Firmware / IoT** | ELF + Qiling + Unicorn + angr for embedded. | [docs/verticals/firmware-iot.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/verticals/firmware-iot.md) |
| 🏁 **CTF / exploit development** | pwndbg + GEF + angr + AFL++ + honggfuzz + LibAFL + Unicorn + ret-sync all behind one hub. | [docs/verticals/ctf-pwn.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/verticals/ctf-pwn.md) |

## Ethics & responsible use

This project exists for **security research, cheat detection, defensive engineering, game-preservation, and reverse-engineering education**. Specifically:

- Anti-cheat engineers use it to understand bypass vectors and harden their systems.
- Red teams use it on binaries they are authorized to analyze.
- Students use it to learn how PE / ELF / IL2CPP / UE4 / Source2 actually work.
- Preservation groups use it to document archived game ecosystems.

**It is not a cheat.** It writes no code into any game. It automates no play. Use it against binaries you own or are authorized to analyze. Do not use it to grief, de-fraud, or harm other players.

Read [SECURITY.md](https://github.com/1llu50ry/mcp-reverse/blob/main/SECURITY.md) for responsible disclosure. By contributing you agree to [CODE_OF_CONDUCT.md](https://github.com/1llu50ry/mcp-reverse/blob/main/CODE_OF_CONDUCT.md).

---

## Features

### Skill Library

- **177 hand-written skills** -- deep technical references on injection, hooking, kernel drivers, anti-cheat internals, ESP/aimbot architecture, and more
- **3,985 archived projects** -- full source code snapshots from the game security ecosystem (prefixed `ags-`)
- Each skill has a `SKILL.md` (description, metadata, topics) and optionally a `source.txt` (complete source tree dump)

### Agents

| Agent | Description |
|-------|------------|
| `reverse-engineer` | Disassembly analysis, struct recovery, offset hunting, binary patching |
| `exploit-developer` | Kernel exploits, BYOVD chains, EFI persistence, privilege escalation |
| `anti-cheat-analyst` | BattlEye, EAC, Vanguard, VAC, FACEIT internals and bypass research |
| `malware-analyst` | Cheat binary analysis, unpacking, IOC extraction, technique classification |
| `cheat-developer` | ESP, aimbot, triggerbot, overlay rendering, UE/Unity/Source engine internals |
| `driver-developer` | WDM/KMDF drivers, IOCTL comm, memory R/W, stealth loading |
| `hypervisor-researcher` | Intel VMX, AMD SVM, EPT/NPT hooks, HV-based memory access |
| `android-researcher` | Zygisk, KernelSU, frida, IL2CPP dumping, native hooking |
| `network-analyst` | Game protocol RE, packet capture, MITM proxy, server emulation |
| `cs2-specialist` | Counter-Strike 2 / Source 2 internals |
| `valorant-specialist` | Valorant / UE4 fork / Vanguard interaction |
| `fortnite-specialist` | Fortnite / UE5 / EAC interaction |
| `apex-specialist` | Apex Legends / Source fork internals |
| `unreal-engine-specialist` | UE4/UE5 GObjects, GNames, ProcessEvent, SDK gen |
| `unity-specialist` | Unity Mono/IL2CPP, GameObjectManager, metadata |
| `source-engine-specialist` | Source 1/2 ConVar, NetVar, ClientClass |
| `injection-specialist` | All injection methods (manual map, reflective, APC, EFI) |
| `hooking-specialist` | All hook types (VMT, IAT, inline, EPT, syscall) |
| `obfuscation-analyst` | VMProtect, Themida, OLLVM analysis and unpacking |
| `windows-internals-agent` | EPROCESS, PEB/TEB, system calls, object manager |
| `ida-specialist` | IDA Pro scripting, plugins, FLIRT, type libraries |
| `ghidra-specialist` | Ghidra scripting, P-code, extensions |
| `dma-specialist` | DMA/FPGA memory access (PCILeech, Screamer) |
| ...and 52 more game-specific, engine-specific, technique-specific, and tool-specific agents |

### Subagents (161)

| Subagent | Purpose |
|----------|---------|
| `offset-finder` | Cross-reference game offsets across 3,900+ archived sources |
| `code-analyzer` | Classify technique, hook method, stealth measures |
| `pattern-scanner` | Generate and validate IDA-style byte patterns |
| `detection-assessor` | Assess detection risk per anti-cheat system |
| `vulnerability-scanner` | Find exploitable vulns in drivers and binaries |
| `struct-recovery` | Recover C++ structures from memory dumps or IDA |
| `binary-differ` | Diff game updates to track offset changes |
| `source-grep` | Deep search across all 3,985 source archives |
| `hook-planner` | Plan hook chains for specific objectives |
| `import-resolver` | Resolve imports for manual-mapped modules |
| `vtable-mapper` | Map virtual function tables |
| `syscall-stub-generator` | Generate direct/indirect syscall stubs |
| `bone-mapper` | Map skeleton bone indices per game |
| `ac-driver-analyzer` | Deep analysis of anti-cheat kernel driver |
| `stack-spoofer` | Spoof call stack for AC evasion |
| `shellcode-encoder` | Encode shellcode to evade signatures |
| ...and 145 more focused subagents across 16 categories |

### Plugins (114)

| Plugin | Purpose |
|--------|---------|
| `game-offset-db` | Cross-reference offset database for 60+ games |
| `technique-finder` | Find implementation examples across all source code |
| `yara-generator` | Generate YARA detection rules from cheat patterns |
| `driver-catalog` | Vulnerable driver database with exploit primitives |
| `hook-library` | All hook types with code examples and detection vectors |
| `struct-database` | Known game engine structures (UE4/UE5, Source, Unity) |
| `anti-cheat-timeline` | AC update tracking and bypass shelf-life |
| `exploit-chain-builder` | Compose multi-stage exploit chains |
| `signature-generator` | Generate and validate byte patterns |
| `cs2-offsets` / `valorant-offsets` / ... | Per-game offset databases (10 games) |
| `ue4-sdk-reference` / `ue5-sdk-reference` | Engine SDK structure references |
| `ntapi-reference` | Undocumented NT API reference |
| `syscall-table` | Windows syscall numbers per OS build |
| `battleye-detection-db` / `eac-detection-db` / ... | Per-AC detection databases |
| `offset-header-generator` / `hook-template-generator` | Code generation tools |
| ...and 99 more data, reference, and code generation plugins across 11 categories |

### Prompts (148)

| Prompt | Purpose |
|--------|---------|
| `analyze-cheat` | Full architecture analysis of a cheat project |
| `find-bypass` | Find bypass techniques for specific anti-cheat |
| `build-cheat` / `build-esp` / `build-aimbot` | Design cheat systems |
| `reverse-binary` / `reverse-unity-game` / `reverse-unreal-game` | RE workflows |
| `write-driver` / `write-injector` / `write-hook` | Implementation guides |
| `bypass-battleye` / `bypass-eac` / `bypass-vanguard` | AC bypass strategies |
| `spoof-hardware` | HWID spoofing design |
| `analyze-update` | Game update offset migration |
| `exploit-vuln-driver` / `exploit-kernel-bug` | Exploitation guides |
| `implement-backtrack` / `implement-autowall` / `implement-prediction` | Feature implementation |
| ...and 138 more prompts across 14 categories for every game hacking task |

---

## Tools (111 total)

### Workflow Tools

| Tool | Description |
|------|------------|
| `research_technique` | End-to-end technique research with scored keyword ranking |
| `analyze_project` | Full project analysis (SKILL.md + source code) |
| `get_agent_briefing` | Load agent definition with available subagents and plugins |

### Skill Tools

| Tool | Description |
|------|------------|
| `list_skills` | List/filter skills by name or type |
| `read_skill` | Read a skill SKILL.md |
| `read_source` | Read source code with pagination (50KB chunks) |
| `search_skills` | Multi-keyword scored search across names, descriptions, topics |
| `skill_stats` | Library statistics |

### Component Tools

| Tool | Description |
|------|------------|
| `list_agents` / `read_agent` | Browse and read agent definitions |
| `list_subagents` / `read_subagent` | Browse and read subagent definitions |
| `list_plugins` / `read_plugin` | Browse and read plugin definitions |
| `list_prompts` / `read_prompt` | Browse and read prompt templates |

### RE / Debug MCP Integrations (v4.1)

Launch and drive **43** external RE and debugging MCP servers directly from this server. Supported backends: **GhydraMCP, SuperghidraMCP (pyghidra-mcp, +gui), Ghidrathon MCP, ida-pro-mcp, Hex-Rays IDA MCP, Binary Ninja MCP, radare2 MCP, x64dbg MCP Server, WinDbg MCP, Cheat Engine MCP, Frida MCP, Hopper MCP, Vibe-RE, JADX MCP, angr MCP, Capstone MCP, PCILeech/MemProcFS MCP, Memflow MCP, Scylla MCP, dnSpyEx MCP, ReClass.NET MCP, Volatility3 MCP, Wireshark/tshark MCP, mitmproxy MCP, dotPeek MCP, Unicorn MCP, ret-sync MCP, BinDiff MCP, Diaphora MCP, Qiling MCP, unidbg MCP, Reko (OpenReality) MCP, QEMU trace MCP, LLDB MCP, GDB MCP, Burp MCP, YARA MCP, ClrMD MCP, Binja-Ghidra sync MCP, Dolphin DME MCP, Cemu IPC MCP**.

| Tool | Description |
|------|------------|
| `list_re_backends` | List every known RE/debug MCP backend (filter by kind/os/tag) |
| `describe_re_backend` | Full detail for one backend (install, launch, HTTP endpoint, config snippet) |
| `pick_re_backend` | Recommend backend(s) for a described task |
| `re_mcp_config` | Emit a Claude Desktop / Claude Code / Cursor / Codex MCP config snippet |
| `launch_re_backend` | Spawn a backend as a managed child process |
| `stop_re_backend` | Terminate a backend (SIGTERM → SIGKILL after grace) |
| `re_backend_status` | Process status + recent stdout/stderr tail |
| `re_backend_health` | HTTP reachability probe for every backend that declares an endpoint |
| `re_http_call` | Proxy an HTTP request to a running backend |
| `x64dbg_cmd` | Send a command to a running x64dbg plugin (GetDebugState, SetBreakpoint, …) |
| `ghidra_decompile` | Decompile a function via a running pyghidra-mcp / superghidra-mcp |
| `cheat_engine_aob` | AoB (array-of-bytes) scan through a running Cheat Engine bridge |
| `frida_eval` | Evaluate a Frida JS snippet in a target process |
| `run` | Code harness: run JavaScript where every decompile tool is an async function (`await pe_parse({ path })`); helpers you define persist across calls and restarts |
| `ida_run_script` | Run an IDAPython script headless via `idat64` |
| `ghidra_run_script` | Run a Ghidra script via `analyzeHeadless` |
| `install_re_backend` | Run the install commands from the catalog for one backend (with `dryRun` preview) |

### Native TypeScript RE Tools (always available)

Zero-dependency Node TypeScript. No Python, no Ghidra, no IDA needed.

| Tool | Description |
|------|------------|
| `pe_parse` | Parse PE/PE+ -- machine, bits, timestamp, sections (name/VA/size/entropy), imports (DLL + names), exports, overlay, Authenticode |
| `elf_parse` | Parse ELF (32/64, little-endian) -- machine, segments, sections, DT_NEEDED, SONAME, interpreter |
| `macho_parse` | Parse Mach-O (thin + fat) -- CPU, filetype, segments, load commands, LC_LOAD_DYLIB list |
| `dex_parse` | Parse Android DEX -- version, counts, first class names |
| `wasm_parse` | Parse WebAssembly -- version, section layout (standard + custom) |
| `file_identify` | Magic-byte sniff: PE, ELF, Mach-O (thin+fat), DEX, WASM, ZIP/APK/JAR, 7-Zip, gzip, zstd, LZ4, PDF, scripts, Switch NSO/NCA, Xbox 360 XEX, PS4/PS5 FSELF |
| `aob_scan` | IDA-style AoB signature scan over any file (`48 8B ?? ?? ?? ?? ?? E8`) |
| `entropy_scan` | Sliding-window Shannon entropy; flag windows above threshold (packed/encrypted detection) |
| `string_extract` | ASCII + UTF-16LE strings with minimum-length filter |
| `hash_identify` | Scan for MD5/SHA-1/SHA-256/CRC-32/FNV-1a/ChaCha20/Blowfish/AES crypto constants with byte offsets |
| `signature_make` | Make an IDA-style byte signature for a region of a file (with uniqueness check) |
| `file_summary` | Size, SHA-256, Shannon H, magic bytes, head/tail hex |

Nothing is vendored: every integration lives in this repo (`src/native-*.ts`, `plugins-side/`). The RE programs those tools drive (Ghidra + JDK, radare2, UPX, x64dbg, FakePDB, a Python env with frida/angr/capstone/…) are installed by `decompile retools install` — which `decompile setup` and the one-line installers run by default.

### Advanced Native Parsers

| Tool | Description |
|------|------------|
| `minidump_parse` | Parse Windows minidump (.dmp): streams, modules, threads, exception, system info |
| `pdb70_identify` | RSDS record -> GUID + age + PDB path + Microsoft symbol server URL |
| `rich_header_parse` | Rich header entries (MSVC build fingerprint) |
| `demangle` | MSVC + Itanium (GCC/Clang) C++ name demangler |
| `assetbundle_parse` | Unity AssetBundle header (UnityFS/Web/Raw/Archive) |
| `pak_parse` | UE4/UE5 .pak footer (magic 0x5A6F12E1, index offset+size+SHA1) |
| `il2cpp_metadata_parse` | Unity IL2CPP global-metadata.dat header (unencrypted) |
| `nso_parse` | Switch NSO header (segments + module id) |

### Workflow Tools

| Tool | Description |
|------|------------|
| `offset_diff` | Diff two offset JSON maps (added/removed/changed) |
| `offset_merge` | Merge N offset sources with voting quorum |
| `sig_validate_cross_build` | Check an AoB signature is unique across several builds |
| `ac_risk_report` | Risk matrix: technique × AC → tier (A/B/C/X) |
| `generate_cheat_sheet` | Markdown cheat sheet per game |

### Agent Mesh — multi-agent collaboration

Lets Claude Code, Codex/ChatGPT, Cursor, Copilot, Gemini CLI and custom bots share one workspace through MCP: register, DM + channel broadcast, task handoff with status machine, adversarial voting on findings, shared KV knowledge base, named locks. Persistence to JSON (zero npm deps). See [docs/agent-mesh.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/agent-mesh.md).

Tools (15): `mesh_agent_register`, `mesh_agent_list`, `mesh_agent_heartbeat`, `mesh_send`, `mesh_read`, `mesh_task_create`, `mesh_task_update`, `mesh_task_list`, `mesh_task_vote`, `mesh_kb_set`, `mesh_kb_get`, `mesh_lock_acquire`, `mesh_lock_release`, `mesh_lock_list`, `mesh_stats`.

### MCP Hub — aggregate backend MCPs

Our server connects to other MCPs (ghidra, ida, x64dbg, binja, radare2, cheat-engine, frida, …) as a CLIENT and re-exposes their tools. Composable: `smart_decompile` picks the first available decompiler backend; `hub_consensus_call` fans out across backends for adversarial comparison. See [docs/mcp-hub.md](https://github.com/1llu50ry/mcp-reverse/blob/main/docs/mcp-hub.md).

Tools (6): `hub_connect`, `hub_list`, `hub_call`, `hub_disconnect`, `smart_decompile`, `hub_consensus_call`.

### CLI

```bash
decompile stats # library counts
decompile lookup battleye # print SKILL.md
decompile search anti-cheat # keyword search
decompile tools # list every MCP tool
decompile health [url] # probe /healthz
decompile serve # start the MCP server
```

### Path sandbox (security)

File-reading tools (`pe_parse`, `elf_parse`, `aob_scan`, `zip_parse`, …) obey `MCP_FS_ALLOW` and `MCP_FS_DENY`. Default is open mode. Set `MCP_FS_ALLOW=/path/a,/path/b` to restrict reads when exposing the server over HTTP.

### HTTP transport, health, metrics

Set `MCP_TRANSPORT=http` to run the server over Streamable HTTP instead of stdio:

```bash
MCP_TRANSPORT=http MCP_HTTP_PORT=7777 MCP_HTTP_HOST=127.0.0.1 node dist/index.js
# → MCP endpoint: POST http://127.0.0.1:7777/mcp
# → readiness: GET http://127.0.0.1:7777/healthz
# → Prometheus: GET http://127.0.0.1:7777/metrics
```

### Tests

```
npm test
```

Node's built-in test runner over `tests/*.test.mjs` (17 cases covering pattern parse, AoB scan, Shannon, string extraction, crypto-constant ID, signature make, PE parse, WASM parse, ELF rejection).

CI runs on push + PR (Node 18/20/22 matrix): [.github/workflows/ci.yml](https://github.com/1llu50ry/mcp-reverse/blob/main/.github/workflows/ci.yml).

---

## Installation

### Requirements

- Node.js 18+
- npm

### Build

```bash
cd decompile
npm install
npm run build
```

### Connect to Claude Code

Add to your MCP settings:

```json
{
 "mcpServers": {
 "gamehacking": {
 "command": "node",
 "args": ["/path/to/decompile/dist/index.js"]
 }
 }
}
```

### Connect to Claude Desktop

Add to `claude_desktop_config.json`:

```json
{
 "mcpServers": {
 "gamehacking": {
 "command": "node",
 "args": ["/path/to/decompile/dist/index.js"]
 }
 }
}
```

### Connect to Cursor

Add to `.cursor/mcp.json`:

```json
{
 "mcpServers": {
 "gamehacking": {
 "command": "node",
 "args": ["/path/to/decompile/dist/index.js"]
 }
 }
}
```

---

## Usage Examples

### Research a technique

```
> research_technique("EPT hook")

Found 12 relevant skills (showing top 10):
- ags-budget-ept (score:7) -- BudgetEPT: stealthy inline EPT-like hooks...
- ags-hyper-deceit (score:6) -- HyperDeceit: HvcallCodeVa hook framework...
```

### Analyze a project

```
> analyze_project("ags-kdmapper", focus="architecture")

# kdmapper
Most popular kernel driver mapper using iqvw64e.sys...
## Source Code (first 300 lines)
...
```

### Search skills

```
> search_skills("valorant vanguard bypass")

Found 23 skills:
- vgk-internals-callbacks (score:7)
- ags-valorant-external (score:4)
```

### Agent briefing

```
> get_agent_briefing("exploit-developer")

# Agent: exploit-developer
Kernel exploit and driver development agent...
## Available Subagents: offset-finder, detection-assessor
## Available Plugins: game-offset-db, technique-finder
```

---

## Project Structure

```
decompile/
+-- src/index.ts # MCP server (16 tools)
+-- dist/ # Compiled JS
+-- skills/ # 4,161 skill directories
| +-- <hand-written>/ # 177 curated deep-dive skills
| +-- ags-*/ # 3,985 archived projects
| +-- SKILL.md # description + metadata
| +-- source.txt # full source tree snapshot
+-- agents/ # 75 agents across 7 categories
| +-- games/ (15) # CS2, Valorant, Fortnite, Apex, etc.
| +-- engines/ (10) # UE4/5, Unity, Source, CryEngine, etc.
| +-- anti-cheat/ (10) # EAC, BE, Vanguard, FACEIT, Byfron, etc.
| +-- kernel/ (10) # drivers, HV, firmware, DMA, EPT
| +-- techniques/ (10) # injection, hooking, obfuscation, etc.
| +-- tools/ (10) # IDA, Ghidra, WinDbg, Frida, x64dbg
| +-- core/ (10) # RE, exploits, cheatdev, malware, etc.
+-- subagents/ # 161 subagents across 16 categories
| +-- offsets/ (10) +-- patterns/ (10)
| +-- code-analysis/(10) +-- anti-cheat/ (11)
| +-- kernel/ (10) +-- injection/ (10)
| +-- hooks/ (10) +-- rendering/ (10)
| +-- memory/ (10) +-- network/ (10)
| +-- game-data/ (10) +-- stealth/ (10)
| +-- reversing/ (10) +-- platform/ (10)
| +-- build/ (10) +-- testing/ (10)
+-- plugins/ # 114 plugins across 11 categories
| +-- game-offsets/ (11) +-- engine-sdks/ (10)
| +-- anti-cheat/ (10) +-- windows-int/ (10)
| +-- technique-ref/(13) +-- tool-finders/ (10)
| +-- code-gen/ (10) +-- binary-anal/ (10)
| +-- crypto/ (10) +-- detection/ (10)
| +-- rendering/ (10)
+-- prompts/ # 148 prompts across 14 categories
| +-- build/ (11) +-- write/ (16)
| +-- implement/ (11) +-- reverse/ (10)
| +-- bypass/ (10) +-- analyze/ (10)
| +-- design/ (10) +-- exploit/ (10)
| +-- compare/ (10) +-- debug/ (10)
| +-- generate/ (10) +-- migrate/ (10)
| +-- optimize/ (10) +-- setup/ (10)
+-- package.json
+-- tsconfig.json
```

---

## Skill Categories

### Hand-Written (177)

| Category | Examples |
|----------|---------|
| Kernel / Drivers | kernel-cr3-physmem, kernel-hooks-ssdt, vulnerable-driver-exploits |
| Injection | reflective-dll, pe-injection-remote, early-bird-apc, threadpool-wait |
| Anti-Cheat | vanguard (15+ vgk-* skills), battleye, eac, patchguard, hvci |
| Game Engines | unreal-object-model, source-netvars, world-to-screen, present-hook |
| Obfuscation | fix-vmp-themida-ollvm, control-flow-flattening, mixed-boolean-arithmetic |
| UEFI / EFI | efi-driver-bootkit, vgk-secure-boot-spoof |
| DMA | dma, iommu, iommu-state-verification |

### Archived Projects (3,985)

Sourced from [awesome-game-security](https://github.com/gmh5225/awesome-game-security):

- **60+ games**: CS2, Valorant, Fortnite, Apex, PUBG, Rust, R6, EFT, Overwatch, Genshin, etc.
- **Techniques**: injection, hooking, DMA/FPGA, driver comm, overlays, kernel exploits
- **Anti-cheat research**: BattlEye, EAC, Vanguard, VAC, FACEIT, Byfron
- **Tools**: IDA plugins, Ghidra scripts, debugger extensions, dumpers, unpackers
- **Platforms**: Windows kernel, Android (Zygisk/KernelSU/Magisk), iOS, Linux

---

## Tech Stack

- **Runtime**: Node.js 18+
- **Language**: TypeScript
- **Protocol**: MCP via `@modelcontextprotocol/sdk`
- **Transport**: stdio

---

## License

This project aggregates publicly available research materials and open-source project snapshots for educational and security research purposes.

---

# decompile (RU)

MCP-сервер для геймхакинга и реверс-инжиниринга. База знаний из **4,100+ скиллов** с полными архивами исходного кода, специализированными агентами и инструментами.

## Возможности

- **177 вручную написанных скиллов** -- инъекции, хуки, ядерные драйверы, внутренности античитов, архитектура ESP/аимбота
- **3,985 архивированных проектов** -- полные снимки исходного кода из экосистемы игровой безопасности
- **75 агентов** (7 категорий) -- по играм (CS2, Valorant, Fortnite, Apex...), движкам (UE, Unity, Source, CryEngine...), античитам (EAC, BE, Vanguard, FACEIT...), ядру (драйверы, HV, DMA, EPT), техникам (инъекции, хуки, обфускация), инструментам (IDA, Ghidra, WinDbg, Frida)
- **161 субагент** (16 категорий) -- поиск офсетов, анализ кода, паттерны, диффы бинарников, grep по 3985 архивам, планирование хуков, восстановление структур, аудит драйверов, стелс, рендеринг, сеть и ещё 145
- **114 плагинов** (11 категорий) -- базы офсетов по 10+ играм, справочники SDK, каталог уязвимых драйверов, детект-базы по каждому античиту, генераторы кода, анализаторы бинарников, крипто, рендеринг

---

[Read more](https://github.com/1llu50ry/mcp-reverse)
تنزيل الأداة

الأكثر شعبية

عرض الكل →

اكتشف الأدوات الأكثر استخدامًا من قبل مجتمعنا.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 مجموعة أدوات OSINT المثالية: رسم بياني للتحقيق، وتقييم الثقة، وعائلات الأسماء المستعارة، وخريطة، وخط زمني، وتقارير. 49 وحدة، وأكثر من 400 موقع، دون الحاجة إلى مفاتيح API.

    994
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # تطبيق GhostLock للتنفيذ بنقرة واحدة (CVE-2026-43499)

    656
  • 3

    looking-glass

    anonghosty/looking-glass

    منصة CSIRT تستقبل تقارير Shadowserver في MongoDB وتعيد عرضها كخرائط تفاعلية وتحليلات ونتائج وإرشادات ولوحات معلومات تنفيذية.

    422
  • 4

    jumpserver

    jumpserver/jumpserver

    JumpServer هي منصة مفتوحة المصدر لإدارة الامتيازات (PAM) توفر لفرق DevOps وتكنولوجيا المعلومات وصولًا آمنًا عند الطلب إلى نقاط نهاية SSH وRDP وKubernetes وقواعد البيانات وRemoteApp عبر متصفح الويب.

    389
  • 5

    SafeLine

    chaitin/safeline

    WAF مستضافة ذاتيًا ووكيل عكسي يقوم بتصفية حركة المرور HTTP الضارة، ويمنع هجمات SQL injection و XSS وهجمات البوت، مع تحديد معدل الطلبات وتشفير HTML/JS الديناميكي.

    333
  • 6

    ARTEX

    baarai/artex

    منصة اختبار اختراق مستقلة متعددة الوكلاء تعتمد على LLM، مع وكلاء تخطيط وتنفيذ، ومخططات للأصول والاستكشاف، وتسجيل حركة مرور MITM، وإعادة اختبار الثغرات.

    330

استكشف جميع الأدوات

تصفح مجموعتنا من الأدوات

عرض جميع الأدوات →