Reverse engineer malware with agents, from packed droppers down to memory-resident payloads.
Malvex is a local-first orchestration harness that connects AI agents to 126 reverse-engineering and malware-analysis tools through MCP (Model Context Protocol). Point it at a binary, a memory dump, a document, or a packet capture. Malvex triages the sample, fans out parallel agents over IDA, Ghidra, radare2, Frida, volatility3, YARA, and dozens of other backends, and returns evidence-grounded findings — IOCs, MITRE ATT&CK mappings, detection rules, and attack-chain graphs — without uploading anything.
AI-driven malware analysis framework with 30+ integrated tools, web REPL, and MCP server
Analysis runs locally. Results include the evidence and limitations behind each conclusion.
Important rule: LLM output is not evidence.
The model may propose hypotheses, likely function names, algorithm matches, or ATT&CK mappings.
Malvex treats those as analyst leads until they are tied to static or runtime evidence.
What it analyzes
Target
What Malvex recovers
Backends
Native binaries (PE, ELF, Mach-O, FAT)
Pseudocode, call graphs, xrefs, imports, strings, resources, compiler/packer ID
./setup.sh # install Rust + tools + MCP servers + Claude Code
malvex doctor # what analysis tools + MCP servers are available
malvex doctor --install # install missing open-source tools
malvex mcp-setup --install # wire RE MCP servers into Claude Code
malvex run /path/to/sample --dry-run # print the plan + agent commands (0 tokens)
malvex run /path/to/sample # full pipeline
Six stages, each spawning parallel agents. Agents share state through MCP (muster blackboard + claude-mem). No finding reaches confirmed without independent evidence reproduction.
The full pipeline SVG is available in the web UI at /settings.
Tooling matrix
Disassemblers & decompilers
Tool
License
Mac
Windows
Linux
Access
IDA Pro
commercial
✓
✓
✓
MCP ida-pro-mcp / re-mcp
Ghidra
open
brew
choco
apt
MCP ghidra-mcp / headless analyzeHeadless
radare2
open
brew
choco
apt
MCP radare2-mcp / CLI r2
rizin
open
brew
choco
apt
CLI rizin
Cutter
open
brew
choco
flatpak
MCP cutter-mcp
Binary Ninja
commercial
✓
✓
✓
MCP binaryninja-mcp
Binary surface & metadata
Tool
License
Mac
Windows
Linux
Purpose
otool
open
xcode
—
—
Mach-O load commands, dylibs, entitlements
codesign
open
xcode
—
—
Signature + hardened runtime checks
class-dump
open
✓
—
—
Objective-C runtime metadata extraction
readelf
open
brew
—
apt
ELF headers, sections, symbols, relocations
objdump
open
brew
—
apt
Section dumps, disassembly, imports
nm
open
brew
—
apt
Symbols and export surface
strings
open
brew
—
apt
Fast ASCII/Unicode extraction
exiftool
open
brew
choco
apt
Metadata from installers, documents, scripts
lief
open
pip
pip
pip
PE/Mach-O/ELF parse + patch (Python)
osslsigncode
open
brew
—
apt
Authenticode parsing for PE samples
checksec
open
brew
—
apt
Mitigation triage: RELRO, Canary, NX, PIE
Malware-specific analysis
Tool
License
Mac
Windows
Linux
Purpose
capa
open
pip
pip
pip
FLARE capability inference from static rules
FLOSS
open
pip
pip
pip
Stack, decoded, and obfuscated string recovery
YARA
open
brew
choco
apt
Signature matching + detection rule validation
ssdeep
open
brew
—
apt
Fuzzy hashing for clustering and lineage
hashdeep
open
brew
—
apt
Recursive hashing for evidence inventories
oletools
open
pip
pip
pip
Office/OLE macro and embedded object triage
volatility3
open
pip
pip
pip
Memory forensics: injections, modules, handles
DIE
open
—
choco
apt
Detect It Easy — packer/compiler identification
PEiD/peframe
open
pip
choco
pip
Packer signature detection
Unpacking & carving
Tool
License
Mac
Windows
Linux
Purpose
UPX
open
brew
choco
apt
Unpack UPX-compressed binaries
binwalk
open
brew
pip
apt
Firmware + embedded blob carving
foremost
open
—
—
apt
File carving from memory dumps
bulk_extractor
open
brew
—
apt
Bulk artifact extraction
msitools
open
brew
choco
apt
MSI table + file extraction
p7zip
open
brew
choco
apt
MSI/CAB/NSIS/InnoSetup unpacking
cabextract
open
brew
choco
apt
CAB decompression
innoextract
open
brew
—
apt
Inno Setup extraction
Emulation & symbolic execution
Tool
License
Mac
Windows
Linux
Purpose
capstone
open
pip
pip
pip
Multi-arch disassembly engine
keystone
open
pip
pip
pip
Assembler engine for patch generation
unicorn
open
pip
pip
pip
CPU emulator — runs packer stubs in isolation
angr
open
pip
pip
pip
Symbolic execution + constraint solving
ropper
open
pip
pip
pip
ROP/JOP gadget search
Dynamic instrumentation & debuggers
Tool
License
Mac
Windows
Linux
Access
Frida
open
pip
pip
pip
MCP frida-mcp / CLI frida-trace
lldb
open
xcode
—
apt
macOS native debugging
gdb
open
brew
choco
apt
Linux/cross debugging
x64dbg
open
—
choco
—
Windows user-mode debugging
WinDbg
commercial
—
winget
—
Kernel + user debugging
strace
open
—
—
apt
Linux syscall tracing
ltrace
open
—
—
apt
Linux library-call tracing
Network analysis
Tool
License
Mac
Windows
Linux
Purpose
mitmproxy
open
brew
pip
apt
TLS intercept for C2 and update-channel analysis
tshark
open
brew
choco
apt
CLI packet analysis: DNS, HTTP(S), JA3
tcpdump
open
brew
—
apt
Raw packet capture for sandbox evidence
MCP orchestration
Tool
Kind
Purpose
claude-mem
MCP plugin
Persistent cross-run memory of findings + context
muster
MCP server
Blackboard + budget shared across parallel agents
MCP servers
Malvex can auto-install and wire these MCP servers into your AI agent via malvex mcp-setup --install:
Evidence-driven pipeline: 15 specialized agents with hypothesis-evidence-verification model
200+ malware analysis tools: from triage to advanced forensics
malvex setup # installs everything including REA
npx rea-agents setup # or manually configure REA for Claude Code
When REA is available, Malvex agents automatically prefer REA's unified MCP interface
for disassembly, decompilation, and cross-reference analysis — falling back to direct
tool invocation only when REA is not installed.
MCP server mode
malvex serve exposes 30 analysis tools over MCP (JSON-RPC 2.0, stdio transport). Any AI agent — Claude Code, Cursor, Windsurf, Cline, Codex — can connect and use them directly.
# Register with Claude Code
claude mcp add malvex -- malvex serve
# Or run standalone
malvex serve --transport stdio
Available MCP tools
Category
Tool
What it does
Pipeline
malvex_analyze
Full analysis pipeline on a target
malvex_triage
Quick triage: hashes, format, packer, entropy
malvex_doctor
Environment check: tools, MCPs available
malvex_sessions
List completed analysis sessions
malvex_findings
Retrieve findings from a session
malvex_coverage
Taxonomy coverage report
malvex_extract
Unpack MSI/CAB/NSIS installers
malvex_reparse
Re-derive findings (no LLM)
Discovery
malvex_tools_available
List installed tools with versions
Triage
malvex_hash
All hashes: MD5, SHA1, SHA256, ssdeep, imphash, TLSH
Each tool automatically selects the best available backend (e.g. malvex_disasm tries radare2, then Ghidra, then IDA) and returns structured output. Tools that require external backends report exactly what to install if missing.
Example prompts (Claude Code / OpenCode / Windsurf / Cursor)
After malvex setup, use these prompts directly in your editor. Malvex runs headless via MCP.
Binary analysis
Use Malvex to analyze suspicious.exe — full triage, static RE, and IOC extraction
Use Malvex to decompile the main function of dropper.dll and explain the C2 protocol
Use Malvex to list imports of ransomware.exe and flag crypto API usage
Use Malvex to scan payload.bin with YARA and map findings to MITRE ATT&CK
Use Malvex to triage packed.exe — detect packer, entropy, and embedded strings
Use Malvex to extract IOCs from cobalt_beacon.bin — IPs, domains, URLs, hashes
Document analysis
Use Malvex to extract and analyze VBA macros from invoice.docm
Use Malvex to parse malicious.pdf for embedded JavaScript, /Launch, and /OpenAction
Use Malvex to check report.rtf for embedded OLE objects and shellcode
Use Malvex to triage spreadsheet.xlsm — macros, auto-open, suspicious strings
Use Malvex to analyze phishing.docx for template injection and remote URLs
Memory and network
Use Malvex to analyze memory.dmp — injections, hollowed processes, decrypted config
Use Malvex to analyze traffic.pcap — C2 beaconing, DNS tunneling, exfiltration
Use Malvex to scan memory dump for RWX regions and reflective DLL loading
Pipeline and orchestration
Use Malvex to run a full analysis pipeline on sample.exe with 3 parallel agents
Use Malvex to plan (dry-run) analysis of installer.msi — show what it would do
Use Malvex to check tool health — what analysis tools and MCPs are available
Use Malvex to list my previous analysis sessions
Single tool invocation
Use Malvex to hash sample.exe — MD5, SHA1, SHA256, ssdeep, imphash
Use Malvex to run capa on loader.dll and show ATT&CK capabilities
Use Malvex to disassemble function at 0x401000 in backdoor.exe
Use Malvex to extract strings from firmware.bin — URLs, IPs, paths, registry keys
Agents
Malvex drives 15 orchestrated agent roles, each with a specific mission and owned vectors:
Agent
Role
triage
Hashes, real type, architecture, packer, entropy, strings, initial IOCs
One agent invokes many skills. See agents/ for the full system prompts.
Skills
61 active malware-analysis skills aligned to the MITRE ATT&CK matrix. Each skill is a concrete procedure: which tool to run, what to grep, what pattern proves the vector, and what evidence to return.
See SKILLS.md for the full skill index and usage guide.
Generated detections (YARA/Sigma with validation results)
The workflow: hypothesis → evidence → verification → confidence.
Similarity is not attribution. ATT&CK mappings, family matches, and lineage are derived outputs — they never substitute for primary evidence.
Layout
crates/
malvex-core shared types (Target, Finding, Severity, Tool)
malvex-doctor tool detection + install + MCP registry
malvex-orchestrator pipeline orchestration, execution, parsing, PoC validation
malvex-cli `malvex` binary
malvex-web web UI (axum upload + session review)
agents/ 15 agent system prompts (markdown)
skills/ 61 SKILL.md procedures aligned to the malware analysis matrix
vulns/
taxonomy.yaml analysis vectors owned by the active agents
attack-chains.yaml curated exploitation chains
config/
headless-tooling.yaml tool preferences per platform
runtime-profiles.yaml agent runtime configurations
tools/
yara_mcp.py YARA MCP compatibility shim
plugins/
ida/ IDA Pro analysis plugins
setup.sh / .ps1 / .bat environment bootstrap scripts
Setup
macOS / Linux
./setup.sh
Idempotent. Installs (in order): Rust toolchain, open-source RE tools (radare2, Ghidra, YARA, binwalk, mitmproxy, lief, capstone, frida-tools, capa, FLOSS, volatility3, oletools, unicorn, angr), Claude Code CLI, uv/pipx helpers. Then builds malvex, runs malvex setup, and starts malvex-web.
Windows
setup.bat
Launches setup.ps1 (elevated). Installs via winget/choco/pip: radare2, rizin, x64dbg, WinDbg, Ghidra, Frida, YARA, lief, 7zip, Claude Code. Builds malvex.exe.
Kali Linux
malvex setup and malvex doctor --install auto-detect Kali via /etc/os-release and install a broad apt-based malware-analysis bundle (38 packages) in addition to per-tool installs.
Notes
On macOS, several packages depend on Homebrew and should be run as a non-root user.
Commercial tools (IDA, Binary Ninja, WinDbg) are detected and reported, never auto-installed.
MCP bridges may show as configured before they show as healthy. Backends need their local tool active.
Cross-platform analysis
Static reverse engineering is host-independent — IDA (via idalib MCP), Ghidra, radare2, and lief all parse Windows PE from macOS. The full static pipeline runs on a Mac against .exe/.dll/.msi targets. malvex extract unpacks MSI/CAB on macOS.
Dynamic instrumentation runs natively when the host OS matches the target platform. Cross-host, agents emit a concrete needs-<platform>-runtime plan with exact steps, hooks, breakpoints, and expected artifacts — never fabricated evidence.
Building
cargo build --release
cargo test --release -p malvex-orchestrator
./target/release/malvex doctor
Disclaimer
Malvex provides tools for lawful malware analysis, reverse-engineering research, and detection engineering. You are responsible for obtaining any required authorization and complying with applicable laws. Analysis runs locally on your machine.
License
MIT
M
Malvex
JoasASantos·44 Sterne·
AI-driven malware analysis framework with 30+ integrated tools, web REPL, and MCP server
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Fragen
Wie installiere ich Malvex?
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
Benötigt Malvex einen API-Schlüssel?
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Welchen Transport verwendet Malvex?
Malvex läuft lokal über stdio.
Wann wurde Malvex zuletzt geprüft?
Zuletzt geprüft: 2026-11-05. AI-driven malware analysis framework with 30+ integrated tools, web REPL, and MCP server