There’s a moment every analyst knows — the one where an unknown file lands on your desk and the clock starts ticking. You need answers, and you need them fast. MalChela was built for exactly that moment.
Today I’m excited to announce the MalChela Video Series on YouTube — a growing collection of tutorial episodes walking through real malware analysis workflows using MalChela, the open-source Rust-based toolkit I’ve been building for the DFIR community. Whether you’re new to the tool or already running it in your lab, there’s something here for you.
Four episodes are available right now in the playlist.
What’s in the Playlist
Ep0 | Installation & First Run
Every case starts somewhere. Episode 0 is your onboarding — installing MalChela, walking through its dependencies, and getting oriented with both the CLI and GUI modes. If you’ve been curious about the tool but weren’t sure where to start, this is the episode to bookmark.
Ep1 | First Contact: Hash, Inspect, Identify
You’ve just been handed a suspicious file. What do you do first?
This episode covers the first three tools in a malware triage workflow — the exact sequence I reach for every time I encounter an unknown file:
hashit — generate MD5, SHA1, and SHA256 hashes to protect chain of custody and enable deduplication
fileanalyzer — static inspection: entropy analysis, PE header fields, compile timestamps, and import tables
malhash — simultaneous lookup against VirusTotal and MalwareBazaar to identify known malware families
By the end of this episode, you’ll take an unknown file from zero to confirmed malware family identification in under five minutes — no sandboxing required.
Ep2 | From Strings to Signatures
Continuing from Episode 1, we go deeper into the confirmed RedLine info-stealer sample using mStrings — MalChela’s string extraction engine. Unlike the traditional strings utility, mStrings runs every extracted string through a detection ruleset and MITRE ATT&CK mapping layer simultaneously, turning raw output into actionable intelligence.
We walk through 62 detections, including PDB path artifacts, hard-coded dropper filenames, WMI queries, credential harvesting patterns, anti-debug checks, and a code injection setup. We then feed the extracted IOCs into Strings2YARA to auto-generate a structured YARA rule — and confirm it fires against the sample using File Analyzer.
By the end, you’ll be reading a malware file not as a pile of strings, but as a window into the attacker’s tradecraft.
Ep3 | REMnux Mode & Custom Tools
MalChela doesn’t work in isolation. Episode 3 covers how to extend the toolkit through the tools.yaml config file and how enabling REMnux mode surfaces an entire distro’s worth of malware analysis utilities directly within MalChela’s interface.
We also explore three built-in integrations: Volatility 3 with a dynamic plugin builder, T-Shark with a searchable reference, and YARA-X — a faster, Rust-native rewrite of YARA.
What’s Coming
The series is ongoing. Future episodes will push further into advanced workflows — think directory-scale triage, corpus management, and the AI-assisted analysis capabilities introduced in MalChela’s MCP integration. Stay subscribed and you won’t miss them.
Get Involved
If MalChela is useful in your work, the best thing you can do is help spread the word:
📺 Subscribe to the YouTube channel — Subscribe to the channel and save the playlist so you don’t miss new episodes as they land.
📖 Follow Baker Street Forensics — Writeups, major releases, and workflow deep dives live here.
💬 Share and comment — If an episode clicks for you, pass it along to a colleague or drop a comment on the video. That feedback genuinely shapes what comes next.
The game is afoot. Let’s get to work.
MalChela is open-source and freely available. Find the project on GitHub.
In a previous post I wrote about integrating MalChela with OpenCode on REMnux and giving the AI a quick briefing on the tool suite so it could incorporate them into its analysis workflow. That was a promising proof of concept, but it raised a natural follow-up question: how do you make these integrations more robust, reproducible, and persistent?
Since that post, I’ve been experimenting with three different approaches to bringing MalChela into AI-assisted workflows — each suited to a different environment and use case. This post walks through all three.
Approach 1: The Kali MCP Server (Toby)
The first implementation started with Toby — my portable Raspberry Pi forensics toolkit running a customized Kali Linux build. Toby is designed for headless operation via SSH, which turns out to be exactly the right architecture for an MCP server. The developers of Kali recently added an update to support MCP integrations. (See https://www.kali.org/blog/kali-llm-claude-desktop/)
Model Context Protocol (MCP) is an open standard that allows AI assistants like Claude to interface with external tools and systems in a structured, reliable way. Instead of pasting instructions into a chat window each session, you define your tools once in a server configuration and the AI has consistent, persistent access to them.
The setup leverages an existing open-source mcp-kali-server that exposes Kali’s forensic and security tooling as MCP tools. On the client side (Mac), the claude_desktop_config.json simply points to Toby (or your Kali box) over SSH:
{
"mcpServers": {
"mcp-kali-server": {
"command": "ssh",
"args": [
"-i",
"/Users/dwmetz/.ssh/id_ed25519",
"dwmetz@192.168.10.89",
"mcp-server"
],
"transport": "stdio"
}
}
}
With this in place, Claude Desktop has persistent, session-independent access to Kali’s toolkit running on Toby. No need to re-brief the AI each session — the tools are always available and always described the same way.
Key prerequisite: passwordless SSH key-based auth between your Mac and Toby. If you haven’t set that up:
ssh-keygen -t ed25519
ssh-copy-id user@<toby/kali-ip>
# Then one manual SSH to accept the host key fingerprint
ssh user@<toby/kali-ip>
Adding MalChela to the Kali MCP Server
The mcp-kali-server ships with routes for Kali’s built-in security tools, but MalChela isn’t included out of the box. Adding it requires changes to two files: kali_server.py (the Flask API backend) and mcp_server.py (the FastMCP frontend). Both live at /usr/share/mcp-kali-server/.
How the architecture works:mcp_server.py is what Claude talks to — it defines MCP tool names, descriptions, and parameter schemas. When a tool is called, it POSTs to kali_server.py, which constructs the actual shell command and executes it on Toby. The critical detail is that MalChela’s binaries must be run from within the MalChela workspace directory — running them from an arbitrary working directory causes failures. The cd {MALCHELA_DIR} && prefix in every command handles this.
kali_server.py changes
Add the MALCHELA_DIR constant (update with your MalChela install path) and Flask routes after the existing tool routes, before the health check endpoint:
Important note on malhash: Unlike the other tools which take a file path, malhash takes a hash string as its argument. The route reads a hash parameter and passes it directly to the binary. Passing a filepath to malhash will fail silently — a subtle but critical distinction.
mcp_server.py changes
The MalChela tool definitions need to be added to the setup_mcp_server() function, immediately before the return mcp line.
@mcp.tool(name="malchela_fileanalyzer")
def malchela_fileanalyzer(filepath: str) -> Dict[str, Any]:
"""
MalChela: Static file analysis - hashes, entropy, packing detection,
PE metadata (imports, sections, timestamps), YARA matches, VirusTotal status.
Best first step for any unknown file.
Args:
filepath: Absolute path to the file to analyze
Returns:
Analysis report
"""
return kali_client.safe_post("api/tools/malchela/fileanalyzer", {"filepath": filepath})
@mcp.tool(name="malchela_mstrings")
def malchela_mstrings(filepath: str) -> Dict[str, Any]:
"""
MalChela: String extraction with IOC detection and MITRE ATT&CK mapping.
Applies Sigma-style detection rules, flags suspicious patterns (registry keys,
encoded payloads, suspicious DLL+API combos), maps findings to ATT&CK techniques.
Args:
filepath: Absolute path to the file to analyze
Returns:
String analysis with ATT&CK mappings and IOCs
"""
return kali_client.safe_post("api/tools/malchela/mstrings", {"filepath": filepath})
@mcp.tool(name="malchela_malhash")
def malchela_malhash(hash: str) -> Dict[str, Any]:
"""
MalChela: Query a file hash against VirusTotal and MalwareBazaar.
Returns detection ratio, AV verdicts, first/last seen dates, and sample metadata.
Requires VT_API_KEY env var; MB_API_KEY optional.
Args:
hash: MD5, SHA1, or SHA256 hash string to query
Returns:
Threat intel results from VirusTotal and MalwareBazaar
"""
return kali_client.safe_post("api/tools/malchela/malhash", {"hash": hash})
@mcp.tool(name="malchela_hashit")
def malchela_hashit(filepath: str) -> Dict[str, Any]:
"""
MalChela: Generate MD5, SHA1, and SHA256 hashes for a single file.
Lightweight when you need hashes without full fileanalyzer output.
Args:
filepath: Absolute path to the file
Returns:
File hashes
"""
return kali_client.safe_post("api/tools/malchela/hashit", {"filepath": filepath})
@mcp.tool(name="malchela_fileminer")
def malchela_fileminer(folderpath: str) -> Dict[str, Any]:
"""
MalChela: Scan a folder for file type mismatches and metadata anomalies.
Classifies all files, flags executables disguised as other types.
Args:
folderpath: Absolute path to the folder to scan
Returns:
File classification and anomaly report
"""
return kali_client.safe_post("api/tools/malchela/fileminer", {"dirpath": folderpath})
return mcp
One parameter naming detail worth noting: mcp_server.py receives folderpath from Claude, but must pass it as dirpath in the JSON body to kali_server.py — that’s what the Flask route reads. The tool definition above handles this correctly.
After saving both files, restart the MCP server and restart Claude Desktop.
Testing on an unknown malware sample
[below is the exact response received from Claude]
I’ll run MalChela analysis on that file via Toby. Let me load the tools first.Tools loaded. Running fileanalyzer first for static analysis, then mstrings for IOC/ATT&CK mapping. Let me verify the path exists:File confirmed on Toby. The MalChela MCP tools use local paths — let me run it directly via the Kali execute_command since the MCP path routing doesn’t map Toby paths. I’ll invoke MalChela’s binaries directly:MalChela binaries found. Running the full suite now:That’s already very telling. Now running mstrings for IOC and ATT&CK mapping:Now let me pull the VirusTotal intel on the hash:That’s a solid picture. Here’s the full analysis breakdown:
5 PE sections including .ndata (atypical NSIS section, flagged as suspicious)
159 imports, including the dangerous trio:
GetProcAddress / LoadLibraryExA — dynamic API resolution (evasion)
ShellExecuteExA — process execution
🎯 MITRE ATT&CK Mappings (from mstrings)
Technique
ID
Tactic
Obfuscated Files or Information
T1027
Defense Evasion
Process Injection
T1055
Defense Evasion / Privilege Escalation
Application Layer Protocol: Web Protocols
T1071.001
Command and Control
🌐 Network IOC
http://nsis.sf.net/NSIS_Error — NSIS error handler URL (confirms NSIS wrapper), not inherently malicious but characteristic of GuLoader’s packaging
Summary
This is a live GuLoader sample — an NSIS-wrapped shellcode injector/downloader commonly used as a first-stage payload to retrieve second-stage malware (often AgentTesla, Remcos RAT, FormBook, etc.). The high entropy, dynamic API loading, and process injection indicators are all consistent with GuLoader’s known behavior. Treat this as active malware — do not execute outside an isolated sandbox.
Approach 2: Persistent MalChela Instructions in OpenCode on REMnux
The REMnux OpenCode integration I described in the previous post worked, but it had one friction point: each new session required re-pasting the MalChela context. OpenCode has a solution for this — the AGENTS.md file.
Place an AGENTS.md file in your working directory (or MalChela’s root directory) and OpenCode will automatically load it as persistent context for every session started from that location. This is the most lightweight way to make MalChela tool-aware without building any infrastructure.
Create the file at /home/remnux/Tools/MalChela/AGENTS.md:
# MalChela Tool Instructions for AI Assistants
MalChela is installed at: /home/remnux/Tools/MalChela
All tools are Rust binaries. The execution pattern is:
1. fileanalyzer - establish baseline: hashes, entropy, PE headers
2. mstrings - extract strings, look for IOCs and ATT&CK technique indicators
3. malhash - check community threat intelligence
4. nsrlquery - confirm or rule out known-good status
## Environment Notes
- API keys (VT_API_KEY, MB_API_KEY) should be set in the shell environment
- MalChela integrates with REMnux tools; use REMnux CLI tools in conjunction as needed
- Case management is available via the MalChela GUI if a graphical session is active
When you start an OpenCode session from the MalChela directory, this context is automatically loaded. No manual pasting, no re-briefing.
Once complete I asked it to save the results to the Desktop in markdown.
What was cool to me about this approach is that using the installed REMnux tools, you can take the analysis further after MalChela. In my testing I (OpenCode) analyzed a file with mStrings. We then followed up by running capa against the file. From there we could compare what each tool detected and missed in the sample. (screenshot truncated)
Approach 3: MalChela as a Native MCP Server (Mac)
The most powerful integration is running MalChela as its own dedicated MCP server — making its tools directly available to Claude Desktop alongside the Kali server. This is what we built out as mcp-malchela.
The server is a small Node.js project that wraps MalChela’s binaries with proper MCP tool definitions. The key files are index.js (the server logic) and package.json.
package.json:
{
"name": "mcp-malchela",
"version": "1.0.0",
"description": "MCP server exposing MalChela malware analysis tools",
"main": "index.js",
"dependencies": {
"@modelcontextprotocol/sdk": "^1.0.0"
}
}
index.js — the server defines each MalChela tool with its input schema, executes the binary when called, and streams back results. Note that malhash is handled differently from the other tools — it receives a hash string rather than a filepath, so the argument routing accounts for that explicitly:
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { CallToolRequestSchema, ListToolsRequestSchema } from "@modelcontextprotocol/sdk/types.js";
WMI usage — likely for system enumeration pre-exfil
Bottom Line
This is a Go-compiled password/credential stealer targeting browsers (Firefox cookies, Discord tokens, Yandex Browser), using WebSocket for C2, with WMI-based discovery. It was UPX-packed (this is the unpacked copy), has a zeroed compile timestamp to defeat timestamp-based triage, and was submitted to MalwareBazaar just hours ago — very fresh sample. Do not execute in any environment without proper isolation.
All three approaches solve the same core problem from the original post: making the AI reliably aware of your tools without re-briefing it every session. The right choice depends on your primary analysis environment — or, if you’re like me, you end up running all three.
All of the configuration files discussed here — including the MCP server setup and the are available in the MalChela repository on GitHub. Clone or pull the latest and you should be ready to go. As always, if you run into issues or have ideas for where to take the MCP integration next, open an issue or drop me a note.
As 2025 draws to a close, I’m taking a moment to reflect on what turned out to be one of my most productive years in code. From major releases to entirely new projects, this year saw significant evolution across my DFIR toolkit—driven by real-world incident response needs, classroom teaching experiences, and late-night tinkering sessions fueled by good bourbon and better puzzles.
What started as continuing work on CyberPipe evolved into a year of substantial innovation: creating MalChela for YARA and malware analysis, building a portable Raspberry Pi forensics platform, developing automated timeline generation workflows, and crafting specialized utilities that solve specific problems I encountered in the field. Each tool represents not just lines of code, but practical solutions to challenges that digital forensics and incident response professionals face daily.
Whether you’re a seasoned forensic analyst, an incident responder building your toolkit, or a student just getting started in DFIR, my hope is that these open-source projects make your work a little easier and a lot more efficient. All tools remain freely available on GitHub, because I believe the best way to advance our field is to share knowledge and capabilities openly.
Here’s what kept me busy in 2025:
MalChela – YARA & Malware Analysis Toolkit (Rust)
My flagship project that evolved significantly throughout 2025:
March: Initial release – Combined 10 programs into one Rust workspace for YARA and malware analysis
May: v2.2 “REMnux Release” – Native support for REMnux, integrations with Volatility3, Tshark, YARA-X
June: v3.0 – Major update introducing Case Management system, FileMiner (replacing MismatchMiner), and tool suggestion capabilities based on file characteristics
July: v3.0.1 – Refinements to mStrings, improved MITRE mappings, “Select All” functionality, optimizations for running on Toby
Rust-based malware analysis toolkit combining YARA scanning, file analysis, hash generation, string extraction with MITRE ATT&CK mapping, and automated malware sample extraction from password-protected archives
Multiple specialized utilities including mzhash/xmzhash for corpus generation, file type mismatch detection, entropy analysis, PE structure examination, and fuzzy hashing capabilities
Integrated threat intelligence with VirusTotal and Malware Bazaar API support, NSRL database queries for known-good file filtering, and Sigma rule application for IOC identification
Case management system (v3.0) featuring unified tracking of files, tools, and notes in case.yaml format with auto-saved outputs, tagging, search functionality, and VS Code integration
Extensible architecture supporting custom tool integration via tools.yamlconfiguration, enhanced support for Volatility 3, TShark, and YARA-X, with both GUI and CLI modes (WSL2-compatible on Windows)
October: v5.2 – Improved collection methods with dual disk space validation, SHA-256 hashing of artifacts, single-file reporting, network collection simplification
November: v5.3 – Critical PowerShell 5.1 compatibility fixes, dual validation logic, enhanced reliability across all PowerShell environments
November: CyberPipe-Timeliner – New companion project to CyberPipe that automates the workflow from Magnet Response collections to unified forensic timelines using Eric Zimmerman’s EZ Tools and ForensicTimeliner
July: Released Toby – A compact forensics toolkit built on Raspberry Pi Zero 2 W running customized Kali Linux, designed for headless operation via SSH/VNC, perfect for field analysis and malware triage
July: Toby-Find – Terminal-based command-line helper tool for discovering CLI forensics tools in KALI and REMnux environments, created initially for university teaching
August: Released Crabwise – A lightweight USB benchmarking tool that measures true read/write speeds of USB devices for forensic workflows. Tests write throughput with pseudo-random data and read performance under uncached conditions. Includes logging functionality to track performance across different cables, hubs, and connection paths, helping forensic investigators optimize their hardware setups.
All projects are available on my GitHub at github.com/dwmetz, with detailed documentation on bakerstreetforensics.com. My goal is making DFIR and malware analysis more accessible, automated, and efficient for incident responders and forensic analysts.
Understanding adversary behavior is core to modern forensics and threat hunting. With the release of MalChela 3.0.2, I’ve added a new tool to your investigative belt: MITRE Lookup — a fast, offline way to search the MITRE ATT&CK framework directly from your MalChela workspace.
Whether you’re triaging suspicious strings, analyzing IOCs, or pivoting off YARA hits, MalChela can now help you decode tactics, techniques, and procedures without ever leaving your terminal or GUI. MITRE Lookup is powered by a local JSON snapshot of the ATT&CK framework (Enterprise Matrix), parsed at runtime with support for fuzzy searching and clean terminal formatting. No internet required.
What It Does
The MITRE_lookup tool lets you:
Search by Technique ID (e.g., T1027, T1566.001)
Search by topic or keyword (e.g., ‘RDP’, ‘Wizard Spider’)
Get tactic category, platforms, and detection guidance
Optionally include expanded content with the –full flag
Use from the CLI, MalChela launcher, or GUI modal
Example:
$ ./target/release/MITRE_lookup -- T1059.003
T1059.003 - Windows Command Shell
Tactic(s): execution
Platforms: Windows
Detection: Usage of the Windows command shell may be common on administrator, developer, or power user systems depending on job function. If scripting is restricted for normal users, then any attempt to enable scripts running on a system would be considered suspicious. If scripts are not commonly used on a system, but enabled, scripts running out of cycle from patching or other administrator functions are suspicious. Scripts should be captured from the file system when possible to determine their actions and intent...
MITRE Lookup (CLI)
GUI Integration
Select MITRE Lookup in the left-hand Toolbox menu
Use the input field at the top of the modal to enter a keyword or technique ID (e.g., `T1059` or `registry`)
Use the “Full” checkbox for un-truncated output
“Save to Case” option
Saving for Later
You can save MITRE Lookup results directly from the GUI, either as a standalone markdown file to a designated folder, or into the active Case Notes panel for later reference. This makes it easy to preserve investigative context, cite specific TTPs in reports, or build a threat narrative across multiple tools. The saved output uses clean Markdown formatting — readable in any editor or compatible with case management platforms. This feature is already live in v3.0.2 and will evolve further with upcoming case linkage support.
Markdown view of a MITRE_lookup report
Why MITRE ATT&CK in MalChela?
MalChela already focuses on contextual forensics — understanding not just what an artifact is, but why it matters. By embedding MITRE ATT&CK into your daily toolchain:
You reduce pivot fatigue from switching between tools/web tabs
You boost investigation speed during triage and reporting
You enable a more threat-informed analysis process
Whether you’re tagging findings, crafting YARA rules, or writing case notes, the MITRE integration helps turn technical output into meaningful insight — all from within the MalChela environment.