SkillAgentSearch skills...

mcp_dfir

Disk and Memory Forensics MCP Server

Install / Use

claude mcp add Androsh7 -- npx -y github:Androsh7/mcp_dfir

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

67/100

Supported Platforms

Claude Code
Claude Desktop

Tags

Our assessment of mcp_dfir

mcp_dfir scores 67/100 on our quality scale, 3880th of 4,595 Development & Engineering skills we index.

Its MCP Server is 4.5 KB long, well organised into 16 sections with 5 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
8/15
Adoption
3/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 69/100, with 4 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

mcp_dfir compared with similar skills

All 4 of these similar skills score higher than mcp_dfir; compare them before choosing.

SkillScoreStarsUpdatedFormat
mcp_dfir (this skill)by Androsh76736mo agoMCP Server
Agent-Reachby Panniantong10096.2k3d agoCLAUDE.md
headroomby headroomlabs-ai10075.1k1d agoCLAUDE.md
CowAgentby zhayujie10047.4ktodayCLAUDE.md
ai-job-searchby MadsLorentzen10046.2k3d agoCLAUDE.md

Frequently asked questions

How do I install mcp_dfir?
Run claude mcp add Androsh7 -- npx -y github:Androsh7/mcp_dfir. The install tabs above show the steps for each supported agent.
Which AI agents does mcp_dfir work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is mcp_dfir safe to use?
It declares no license and scores 69/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mcp_dfir still maintained?
The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

MCP DFIR

MCP DFIR (Digital Forensics Incident Response) is an MCP server that gives AI agents the tools to perform memory, disk, and artifact forensics. It runs forensics tools inside an isolated Docker container and exposes them over the MCP stdio transport.

Example report based on the TryHackMe Volatility Essentials room.

Features

  • Memory forensics via Volatility3
  • Disk forensics via The Sleuth Kit
  • File search with strings, grep, and find
  • Archive extraction with unzip and tar
  • Automatic Windows symbol downloading and conversion
  • Linux symbol search and downloading from Abyss-W4tcher/volatility3-symbols
  • Persistent command history — the agent never re-runs commands already completed
  • Analyst notes — the agent records findings in structured markdown notes

Requirements

  • Docker must be installed and running

Installation

pip install mcp-dfir

Setup

Claude Desktop config

Add the following to your Claude Desktop claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-dfir": {
      "command": "python -m mcp_dfir"
    }
  }
}

Case directory layout

The MCP server expects evidence and artifacts to be organized under a case directory:

my_case/
├── evidence/    # Place memory dumps, disk images, etc. here (read-only)
├── artifacts/   # Output location for extracted files (read-write)
├── symbols/     # Volatility symbol files (auto-populated on download)
└── analysis/    # Command history and analyst notes (auto-generated)

Place all evidence files (.mem, .img, .e01, etc.) inside the evidence/ directory before starting a session.

Args

usage: mcp-dfir [-h] [--version] [-d CASE_DIR]

options:
  -h, --help            show this help message and exit
  --version             show program's version number and exit
  -d, --case-dir CASE_DIR
                        Working directory for the case, default: current directory

MCP Tools

| Tool | Description | | ---------------------------- | -------------------------------------------------------------------- | | run_volatility_command | Runs Volatility3 (vol) for memory forensics | | download_windows_symbol | Downloads and converts Windows PDB symbols for Volatility3 | | download_linux_symbol | Downloads a Linux symbol file from Abyss-W4tcher/volatility3-symbols | | search_linux_symbols | Searches the Linux symbol map by regex to find matching symbol files | | run_sleuthkit_command | Runs any Sleuth Kit tool for disk forensics | | run_strings | Runs strings on a file | | run_grep | Runs grep on files | | run_find | Runs find to search for files | | list_files | Lists files in evidence, artifacts, or symbols | | unzip_file | Extracts a zip archive into /artifacts | | untar_file | Extracts a tar archive into /artifacts | | get_hash | Computes a hash of a file | | get_command_history | Returns all previously run commands | | get_command_result | Returns the output of a specific past command | | show_analyst_notes_summary | Lists all analyst notes | | show_analyst_note | Retrieves the content of a specific analyst note | | add_analyst_note | Creates a new analyst note | | update_analyst_note | Updates an existing analyst note |

Build from source

# Create virtual environment
python3 -m venv .venv

# Activate (Linux/macOS)
source .venv/bin/activate
# Activate (Windows)
.venv/Scripts/activate.ps1

# Install dependencies
pip install .[dev]

# Run
mcp-dfir --case-dir /path/to/your/case
# or
python3 -m mcp_dfir --case-dir /path/to/your/case

Related Skills

View on GitHub
GitHub Stars3
CategoryDevelopment
Updated6mo ago
Forks0

Languages

Python

Trust signals

69/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium3 low