FlareVM MCP Server

A Model Context Protocol (MCP) server that provides remote access to Windows malware analysis tools on FlareVM through a unified interface. This enables AI agents and security analysts to perform comprehensive malware analysis and reverse engineering tasks without manual tool interaction. This project is developed to enable agentic AI integration and ease file transfers to and from FlareVM while keeping it isolated.

Quick install

Three supported installation paths:

One-line installer (Kali / Debian)

curl -sSL https://raw.githubusercontent.com/zixuantemp/flarevm-mcp/main/install.sh | bash

Creates a venv at ~/.flarevm-mcp/venv, installs the package, and stores your FlareVM password in the system keyring.

pip (any Linux / macOS / WSL)

pip install git+https://github.com/zixuantemp/flarevm-mcp.git flarevm-mcp   # runs the MCP server on stdio

Docker

docker run -i --rm \     -e FLAREVM_HOST=192.168.100.10 \     -e FLAREVM_USER=xtemp \     -e FLAREVM_PASSWORD=infected \     ghcr.io/zixuantemp/flarevm-mcp

After install, register with your MCP client (~/.claude/.mcp.json or claudedesktopconfig.json) — the installer prints a ready-to-paste snippet.

MCP capabilities

This server implements the full MCP capability set:

• Tools (48) — see resources/tools-reference.md.
• Prompts (5) — pre-baked workflows for common tasks. See prompts/.

- triageunknownsample, behavioralanalysis, unpackworkflow, injectionhunt, persistenceaudit_report.

• Resources (5) — live and static reference material:

- flarevm://tools/inventory — Test-Path every configured tool, live. - flarevm://config/fakenet-default — generated FakeNet config. - flarevm://docs/yara-rules — installed YARA rule listing + index. - flarevm://docs/cheatsheet — common workflow recipes. - flarevm://status/connection — live FlareVM health check.

• Skills (3) — Claude Code skill bundles in skills/:

triage-malware-sample, incident-response-windows, automated-unpacking.

Security

Detonation runs inside a disposable VM, never on the analyst host. See SECURITY.md for the full threat model, credential handling rules, and how to report a vulnerability.

License

MIT — Copyright (c) 2026 zixuantemp.

---

What is FlareVM MCP?

FlareVM MCP is made to bridge between your analysis environment (typically Kali Linux) and an isolated Windows malware analysis VM (FlareVM) to enable analysis on both Linux and Windows environments. It exposes 40+ malware analysis tools through the MCP protocol, allowing:

• Remote file operations - Upload/download samples and artifacts
• Static analysis - Packer detection (DIEC), capability analysis (CAPA), string extraction (FLOSS)
• Dynamic analysis - Process monitoring, network surveillance, registry tracking
• Debuggers - x64dbg scripting, WinDbg crash analysis
• Instrumentation - Frida hooks for runtime API monitoring
• IDA Pro integration - Decompilation and annotation via RPC

Architecture Overview

┌─────────────────────────────────┐
│   AI Agent / Claude Code        │
│  (Kali Linux / Local Machine)   │
└────────────────┬────────────────┘
                 │
              MCP (stdio)
                 │
        ┌────────▼─────────┐
        │  FlareVM MCP     │
        │  Server          │
        │  (Python/FastMCP)│
        └────────┬─────────┘
                 │
    ┌────────────┼────────────────────────┐
    │            │                        │
  WinRM      SMB Share            IDA RPC
    │            │                (localhost)
    │            │                        │
┌───▼────────────▼─────────────────────┐ │
│      FlareVM (Windows VM)            │ │
│  ┌──────────────────────────────────┐ │ │
│  │ Malware Analysis Tools:          │ │ │
│  │ - Procmon (process monitoring)   │ │ │
│  │ - DIE (packer detection)         │ │ │
│  │ - FLOSS (string extraction)      │ │ │
│  │ - CAPA (capability analysis)     │ │ │
│  │ - x64dbg (debugger)              │ │ │
│  │ - WinDbg (dump analysis)         │ │ │
│  │ - Frida (dynamic instrumentation)│ │ │
│  │ - FakeNet-NG (network sim)       │ │ │
│  │ - Autoruns (persistence)         │ │ │
│  │ - Regshot (registry monitoring)  │ │ │
│  │ - IDA Pro (reverse engineering)  │ │ │
│  └──────────────────────────────────┘ │ │
│                                        │ │
│  IDA Pro Server (port 13337)──────────┘ │
└────────────────────────────────────────┘

Current Features

File Transfer Operations

• upload_file - Upload files from Kali to FlareVM (>8KB uses SMB, <8KB uses WinRM)
• download_file - Download analysis artifacts back to Kali
• Automatic SHA256 checksum verification for integrity

Basic System Tools

• check_connection - Verify WinRM connectivity and get system info
• execute_powershell - Run arbitrary PowerShell commands
• read_file - Read file contents remotely
• getfilehash - Calculate MD5/SHA1/SHA256 hashes
• list_processes - Enumerate running processes with optional filtering

Dynamic Analysis

• procmon_start - Start Process Monitor with optional process filtering
• procmon_stop - Stop Process Monitor capture
• procmonexportcsv - Export PML logs to CSV for analysis
• executewithmonitoring - Execute binary with full monitoring (procmon + network)
• monitornetworkrealtime - Real-time network connection monitoring
• processhackerinfo - Detailed process information via Process Hacker
• regshot_snapshot - Registry snapshot (before/after/compare analysis)
• autoruns_analyze - Analyze autostart programs and persistence

Static Analysis

• die_analyze - Detect compiler/packer with DetectItEasy (DIEC)
• flossextractstrings - Extract obfuscated strings with FLOSS
• capa_analyze - Identify malware capabilities with CAPA framework

Dynamic Instrumentation

• fridalistprocesses - List processes available for Frida injection
• fridaspawnand_attach - Spawn and attach Frida to process
• fridaattachpid - Attach to running process by PID
• fridarunscript - Execute Frida instrumentation scripts

Debugging & Analysis

• x64dbg_load - Launch executable in x64dbg GUI
• x64dbgrunscript - Create and execute x64dbg scripts
• windbganalyzedump - Analyze crash dumps with WinDbg

Network Simulation

• fakenet_start - Start FakeNet-NG network simulation
• fakenet_stop - Stop FakeNet-NG and retrieve logs

IDA Pro Integration (Not built-in in FlareVM)

• idagetmetadata - Get metadata about loaded binary
• idalistfunctions - List functions with pagination
• idadecompilefunction - Decompile function to pseudocode
• idadisassemblefunction - Get assembly listing
• idaliststrings - List strings in binary
• idasetcomment - Add/modify comments in IDA
• idarenamefunction - Rename functions

System Requirements

Host Machine (Kali/Analysis)

• Python 3.10+
• python3-winrm - Windows Remote Management library
• smbclient - For large file transfers
• python-keyring - For credential storage
• fastmcp - MCP server framework

FlareVM (Windows Analysis VM)

• OS: Windows 10/11
• WinRM: Enabled and configured for remote access
• SMB Share: Optional but recommended (named KaliShare)
• Tools Required:

- Procmon (SysInternals) - x64dbg - WinDbg - DIEC (DetectItEasy CLI) - FLOSS - CAPA - Frida for Windows - FakeNet-NG - Autoruns (SysInternals) - Regshot - IDA Pro (optional, for IDA tools)

Installation

1. Clone Repository

cd /home/kali
git clone https://github.com/zixuantemp/flarevm-mcp.git
cd flarevm-mcp

2. Install dependencies

# Requires Python > 3.10
pip install -r requirements.txt
sudo apt-get install smbclient

3. Configure Credentials

# Store FlareVM credentials in system keyring
python3 << 'EOF'
import keyring
Configure based on your FlareVM setup
FLAREVM_HOST = "192.168.100.128"  # Adjust to your VM IP
FLAREVM_USER = "USER"            # Adjust to your username
FLAREVMPASSWORD = "yourpassword" # Your password
Store password securely
keyring.setpassword("flarevm", FLAREVMUSER, FLAREVM_PASSWORD)
print(f"✓ Credentials stored for {FLAREVMUSER}@{FLAREVMHOST}")
EOF

4. Update Configuration

Edit server.py to match your environment:

FLAREVM_HOST = "192.168.100.10"      # Your FlareVM IP
FLAREVM_USER = "xtemp"                # Your Windows username
SMBSHARENAME = "KaliShare"          # Your SMB share name
SMBLOCALPATH = "C:\\Share"          # SMB mount point on FlareVM

5. Configure MCP Server

For use with Claude Code or other MCP clients, add to your MCP config:

For Claude Code (~/.claude/claude.json):

{   "mcp_servers": {     "flarevm": {       "command": "python3",       "args": ["/home/kali/mcp-flare/server.py"],       "env": {         "PYTHONUNBUFFERED": "1"       }     }   } }

OR

claude mcp add flare-mcp python3 /path/to/server.py

For other MCP clients, configure according to their documentation.

6. Verify Installation

# Test connection
python3 << 'EOF'
import asyncio
import json
from pathlib import Path
import sys
sys.path.insert(0, '/home/kali/mcp-flare')
async def test():     # This will attempt to load the server     print("✓ Server module loads successfully")     print("✓ All dependencies installed")
asyncio.run(test()) EOF

Configuration Guide

WinRM Setup on FlareVM

• Enable WinRM:

# On FlareVM, run as Administrator:
Enable-PSRemoting -Force
Set-Item WSMan:\localhost\Client\TrustedHosts -Value "*" -Force
Restart-Service WinRM

• Verify connectivity from Kali:

python3 << 'EOF'
import winrm
session = winrm.Session(     "192.168.100.128",     auth=("USER", "password"),     transport='plaintext' )
result = session.run_ps("Write-Output 'Hello from FlareVM'") print(result.std_out.decode()) EOF

SMB Share Setup (Optional)

For large file transfers (>8KB), configure SMB share on FlareVM:

• Create share:

New-Item -Path "C:\Share" -ItemType Directory -Force
New-SmbShare -Name "KaliShare" -Path "C:\Share" -FullAccess "Everyone"

• Test from Kali:

smbclient //192.168.100.128/KaliShare -U xtemp -c "ls"

IDA Pro Integration

If using IDA Pro tools:

• Install IDA Pro on FlareVM
• Install IDA Pro MCP plugin: https://github.com/mandiant/ida-pro-mcp
• Start IDA Pro with MCP server listening on localhost:13337
• Verify on FlareVM:

netstat -ano | findstr :13337

Usage Examples

1. Quick Malware Triage

# Using with Claude Code or Python
from mcp_client import MCPClient
client = MCPClient("flarevm")
Upload sample
client.call("upload_file", {
    "local_path": "/home/kali/samples/malware.exe",
    "remote_path": "C:\\temp\\sample.exe"
})
Get static analysis
dieresult = client.call("dieanalyze", {
    "file_path": "C:\\temp\\sample.exe"
})
print(f"Packer: {die_result}")
Extract strings
strings = client.call("flossextractstrings", {
    "file_path": "C:\\temp\\sample.exe"
})
Get capabilities
caparesult = client.call("capaanalyze", {
    "file_path": "C:\\temp\\sample.exe"
})

2. Behavioral Analysis with Monitoring

# Monitor process execution
result = client.call("executewithmonitoring", {
    "executable": "C:\\temp\\sample.exe",
    "arguments": "--test",
    "duration": 30
})
Download procmon logs
client.call("download_file", {
    "remote_path": result["ProcmonLog"],
    "localpath": "/home/kali/analysis/procmonlogs.pml"
})

3. API Hooking with Frida

# Hook Windows API during execution
frida_script = """
Interceptor.attach(Module.findExportByName("kernel32.dll", "CreateProcessW"), {
    onEnter: function(args) {
        console.log("[*] CreateProcess called with: " + args[1].readUtf16String());
    }
});
"""
result = client.call("fridarunscript", {     "target": "sample.exe",     "scriptcontent": fridascript })

4. Interactive Debugging with x64dbg

# Load in debugger
client.call("x64dbg_load", {
    "executable": "C:\\temp\\sample.exe"
})
Create breakpoint script
script = """
bp 0x00401000
BreakOnDll(kernel32.dll, false)
bp CreateProcessW
"""
client.call("x64dbgrunscript", {     "script_content": script })

5. IDA Pro Analysis

# Decompile function
decomp = client.call("idadecompilefunction", {
    "address": "0x00401000"
})
Add comment
client.call("idasetcomment", {
    "address": "0x00401000",
    "comment": "Entry point - possible C2 setup"
})
Rename function
client.call("idarenamefunction", {
    "function_address": "0x00401050",
    "newname": "decryptconfig"
})

6. Persistence Analysis

# Check autostart programs
autoruns = client.call("autoruns_analyze")
Take registry snapshots
before = client.call("regshot_snapshot", {
    "action": "first",
    "output_dir": "C:\\temp\\regshot"
})
Run malware
client.call("executewithmonitoring", {
    "executable": "C:\\temp\\sample.exe",
    "duration": 30
})
Compare after
after = client.call("regshot_snapshot", {
    "action": "second",
    "output_dir": "C:\\temp\\regshot"
})
comparison = client.call("regshot_snapshot", {     "action": "compare",     "output_dir": "C:\\temp\\regshot" })

Suggested Setups

Setup 1: Minimal Analysis Lab

Components:

• Kali Linux VM (4GB RAM, 20GB storage)
• FlareVM Windows 10 (8GB RAM, 50GB storage)
• Network: Isolated lab network (no internet)
• Storage: Shared folder for samples/logs

Tools Enabled:

• Procmon, x64dbg, DIE, FLOSS, CAPA

Best For: Quick triage, static analysis, basic dynamic analysis

Estimated Setup Time: 2-3 hours

Setup 2: Advanced Research Lab

Components:

• Kali Linux (dedicated host, 8GB+ RAM)
• Multiple FlareVM snapshots (one per sample type)
• IDA Pro for reverse engineering
• Network: Isolated + FakeNet for network-connected malware
• Storage: 500GB+ for analysis artifacts

Tools Enabled:

• All tools: Procmon, x64dbg, WinDbg, DIE, FLOSS, CAPA, Frida, IDA Pro, FakeNet

Workflow:

• Static analysis (DIE, FLOSS, CAPA)
• Behavioral analysis (Procmon, network monitoring)
• Interactive debugging (x64dbg, Frida)
• Deep reverse engineering (IDA Pro)

Best For: Professional malware analysis, research, threat intelligence

Estimated Setup Time: 8-10 hours

Setup 3: Automated Analysis Pipeline

Components:

• Kali Linux (automation host)
• FlareVM (automated analysis)
• Message queue (Redis/RabbitMQ optional)
• Database (SQLite/MongoDB) for results

Workflow:

Sample Upload → Static Analysis → Dynamic Analysis → Report Generation

Best For: Bulk sample analysis, honeypot integration, SOC automation

Estimated Setup Time: 1-2 days

API Reference

Tool Categories

File Transfer

• uploadfile(localpath, remote_path)
• downloadfile(remotepath, local_path)

System Operations

• check_connection()
• execute_powershell(command)
• read_file(path)
• getfilehash(path, algorithm)
• list_processes(filter?)

Dynamic Analysis

• procmonstart(outputfile, process_filter?)
• procmon_stop()
• procmonexportcsv(pmlfile, csvfile)
• executewithmonitoring(executable, arguments?, duration?)
• monitornetworkrealtime(duration?, process_filter?)
• processhackerinfo(processnameor_pid)
• regshotsnapshot(action, outputdir)
• autorunsanalyze(verifysignatures?)

Static Analysis

• dieanalyze(filepath)
• flossextractstrings(filepath, minlength?)
• capaanalyze(filepath)

Debugging

• x64dbgload(executable, scriptfile?)
• x64dbgrunscript(scriptcontent, savepath?)
• windbganalyzedump(dump_file, commands?)

Frida Instrumentation

• fridalistprocesses()
• fridaspawnandattach(executable, scriptpath)
• fridaattachpid(pid, script_path)
• fridarunscript(target, script_content)

Network Simulation

• fakenetstart(configfile?)
• fakenet_stop()

IDA Pro

• idagetmetadata()
• idalistfunctions(offset, count)
• idadecompilefunction(address)
• idadisassemblefunction(start_address)
• idaliststrings(offset, count)
• idasetcomment(address, comment)
• idarenamefunction(functionaddress, newname)

Troubleshooting

Connection Issues

Problem: "could not read Username for ... No such device or address"

Solution: Verify FlareVM IP is reachable ping 192.168.100.10

Problem: "WinRM connection timeout"

Solution: Enable WinRM on FlareVM Run as Administrator on FlareVM:   Enable-PSRemoting -Force   Set-Item WSMan:\localhost\Client\TrustedHosts -Value "*" -Force

Problem: "Keyring password not found"

Solution: Store credentials in keyring python3 -c "import keyring; keyring.set_password('flarevm', 'xtemp', 'password')"

File Transfer Issues

Problem: "SMB connection failed"

Solution: 
Verify SMB share exists: net share
 
Check network connectivity: ping
 
Verify credentials: smbclient -U user

Problem: "File upload verification failed"

Solution: Check available disk space on remote machine diskspace C:\temp\

Tool Execution

Problem: "Tool not found" error

Solution: Verify tool path in server.py matches your FlareVM installation Check: C:\Tools\sysinternals\Procmon.exe

Problem: "Permission denied" on file operations

Solution: Ensure running WinRM as user with appropriate permissions Run: whoami on FlareVM

Security Considerations

Isolation

• Always run FlareVM on isolated network (no internet unless needed)
• Use separate credentials for analysis vs. production systems
• Snapshot FlareVM before executing unknown binaries

Credential Management

• Use system keyring (not hardcoded passwords)
• Rotate credentials regularly
• Use least-privilege user account for WinRM

Network Security

• Restrict WinRM to trusted networks only
• Use VPN if connecting over untrusted networks
• Monitor WinRM traffic for anomalies

Malware Safety

• NEVER execute unknown binaries on host machine
• ALWAYS use FlareVM for suspected malware
• Verify VM snapshots before behavioral analysis
• Use FakeNet for network-connected malware

Contributing

Contributions are welcome! Please:

• Fork the repository
• Create feature branch (git checkout -b feature/amazing-feature)
• Add tests for new functionality
• Update documentation
• Submit pull request

License

This project is provided as-is for security research and malware analysis purposes.

References

• FlareVM GitHub
• Model Context Protocol
• WinRM Documentation
• Frida Dynamic Instrumentation
• IDA Pro MCP Plugin

Support

For issues, questions, or suggestions:

• Open an issue on GitHub
• Check existing documentation
• Review tool-specific documentation

---

Last Updated: 2026-04-17 Version: 1.0.0