ModelsAtlas
Explore
Atlas / MCP servers / axdithyaxo / Forensic Toolkit

Forensic ToolkitSAFE

mcp/axdithyaxo/forensic-toolkit
MCP server by axdithyaxo · Audited 2026-10-09
⚑ Report / re-scanSource ↗

Secure AI-enabled digital forensics toolkit built with Model Context Protocol

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
5 5r · 0w · 0d
Transport
—
License
—
Stars
29
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

MCP Forensic Toolkit is a secure, AI-ready local server for digital forensics, built using the Model Context Protocol (MCP). It exposes semantically meaningful tools to analyze logs, verify file integrity, and generate audit-grade forensic reports. Designed for analysts and LLMs alike, it enables automated investigation with precision and safety.

Features

  • Structured log triage using keyword-based scanning (scan_syslog)
  • File metadata extraction and SHA-256 hashing (file_metadata)
  • Recursive integrity scanning with directory hashing (hash_directory)
  • Correlation engine linking file modifications to log events (correlate_file_and_logs)
  • Human-readable forensic reporting (generate_forensic_report)
  • Secure access control via SAFE_BASE and sandboxed environment
  • Built-in LLM prompts for guided reasoning and forensic tasks

Screenshot

This example demonstrates a successful correlation analysis between a file and system log entries using the generate_forensic_report tool:

Getting Started

Prerequisites

  • Python 3.10+
  • Poetry or pip
  • MCP CLI (pip install modelcontext or follow setup guide)
  • .env file with SAFE_BASE defined

Installation

Dependencies

  • Python >= 3.10
  • Poetry (recommended) or pip for dependency management
  • Key Python packages installed automatically:
  • modelcontext
  • fastapi
  • uvicorn
  • python-dotenv
  • typing-extensions

Using Poetry (recommended)

# Clone the repo
git clone https://github.com/axdithyaxo/mcp-forensic-toolkit.git
cd mcp-forensic-toolkit

# Install Poetry if not already installed
curl -sSL https://instal
Read from source at commit 9b0610441ea6OBSERVED · 2026-10-09
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add mcp-forensic-toolkit -- uvx mcp-forensic-toolkit
claude-desktop
{
  "mcpServers": {
    "mcp-forensic-toolkit": {
      "command": "uvx",
      "args": [
        "mcp-forensic-toolkit"
      ]
    }
  }
}
03

Exposed tools (5)

5 read · 0 write · 0 destructive.

ToolRiskDescription
correlate_file_and_logsread
file_metadataread
generate_forensic_reportread
hash_directoryread
scan_syslogread
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (4)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.Rhistory
.Rhistory
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
README.md:117
http://127.0.0.1:6274
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
requirements.txt
pytest, python-dotenv
Why it matters. 2 requirement(s) not pinned with ==
Fix. pin exact versions

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-09 · audit v0.4.1 · source sha 9b0610441ea6full audit observations/trust-audit/mcp-server/axdithyaxo__forensic-toolkit.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-099b0610441ea6SAFEB89first audit
06

Questions

What is the Forensic Toolkit MCP server?

Secure AI-enabled digital forensics toolkit built with Model Context Protocol

What tools does Forensic Toolkit expose?

5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Forensic Toolkit safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Forensic Toolkit need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (9b0610441ea6), read on 2026-10-09. The repository is watched and re-audited when it changes.

Advertisement