Forensics MCP Server
Self-Assembling Forensic MCP Server (FastMCP / Python)
Ein modularer Digital Forensics and Incident Response (DFIR) Model Context Protocol (MCP) Server, erstellt mit Python und FastMCP (mcp>=2.0.0).
Er erkennt dynamisch Host- und Container-Forensik-Werkzeuge beim Start und baut automatisch funktionale Werkzeuge, Ressourcen und Triage-Prompts für lokale LLMs und KI-Agenten (Ollama, Claude, Cursor, Antigravity usw.) zusammen.
🌟 Funktionen
🔍 Dynamische Fähigkeitserkennung: Durchsucht Host-Umgebungspfade, installierte Binärdateien (
exiftool,strings,volatility3,binwalk,tshark,objdump,gdb,yara) und Docker-Laufzeitumgebungen. Fehlende Werkzeuge werden ohne Absturz gemeldet.🧩 Selbstzusammenbauende Werkzeug-Primitive: Registriert automatisch nur die in der Host-Umgebung verfügbaren Werkzeuge.
🛡️ Netzwerklos & offline bereit: Integrierte Offline-Bedrohungsintelligenz-Datenbank mit bekannten Beispiel-Signaturen (EICAR, WannaCry, Mimikatz) für sichere, datenschutzfreie Incident Response.
📋 Manipulationssichere Beweiskette: Jede Werkzeugausführung, jedes untersuchte Artefakt, jede SHA-256-Prüfsumme und jeder Aktionsparameter wird kryptografisch gehasht und in einem nur-anhängbaren Ledger protokolliert (
evidence/chain_of_custody.jsonl).🩺 Selbstberichtende Gesundheit & Ressourcen: Echtzeit-Fähigkeitsmatrix (
forensics://capabilities), Aufbewahrungsprotokolle (forensics://custody) und Systemgesundheit (forensics://health).⚡ Dualer Transport: Unterstützt standardmäßiges STDIO für native MCP-Clients (Cursor, Claude, Antigravity) und SSE/HTTP für Web-LLM-Agenten (Ollama, Open WebUI).
Related MCP server: findevil-agent
🚀 Schnellstart
1. Voraussetzungen
Python 3.10+ (oder uv)
2. Server starten
Option A: Nativer STDIO-Transport (Für lokale Agenten / Cursor / Claude)
cd /home/b47m4n/Projects/forensics-mcp-framework
uv run src/server.pyOption B: SSE / HTTP-Transport (Für Web / Remote-LLMs)
cd /home/b47m4n/Projects/forensics-mcp-framework
uv run src/server.py --transport sse --port 8000🔌 Verbindung zu lokalen LLMs & Agenten
1. Antigravity / Claude / Cursor (claude_desktop_config.json / mcp.json)
{
"mcpServers": {
"forensic-analyzer": {
"command": "uv",
"args": [
"--directory",
"/home/b47m4n/Projects/forensics-mcp-framework",
"run",
"src/server.py"
]
}
}
}2. Lokales LLM via Ollama + MCP
Verbinden Sie Ihr lokales Modell (z. B. llama3.1, qwen2.5-coder) über den SSE-Endpunkt:
http://localhost:8000/sse
🛠️ Katalog der erkannten Werkzeuge
Werkzeug | Kategorie | Dynamische Bedingung | Beschreibung |
| Metadaten & Dateien | Immer verfügbar | Berechnet Hashes (MD5/SHA256), EXIF-Tags und erkennt MIME-Konflikte |
| Statische Analyse | Immer verfügbar | Extrahiert druckbare ASCII- und Unicode-Zeichenfolgen |
| Bedrohungserkennung | Immer verfügbar | Durchsucht nach C2-URLs, IP-Adressen, Base64-Blobs, Befehlsausführung |
| Bedrohungsintelligenz | Immer verfügbar | Überprüft Hashes gegen Offline-Signaturen und optionale Live-APIs |
| Diagnose | Immer verfügbar | Gesundheitsstatus, Speicherprüfung und Werkzeugbereitschaft |
| Speicherforensik |
| Volatility 3 |
| Speicherforensik |
| Volatility 3 |
| Speicherforensik |
| Volatility 3 |
| Speicherforensik |
| Volatility 3 |
| Speicherforensik |
| Volatility 3 |
| Datei-Carving |
| Firmware-Signatur- und Dateisystem-Carving |
| Netzwerkforensik |
| Analysiert PCAP-Netzwerkpaketerfassungen |
| Reverse Engineering |
| Disassembliert binäre Maschinenbefehle |
| Debugging |
| Automatisierte Batch-Debugging-Inspektion |
| Signaturerkennung |
| Durchsucht Beweismittel nach YARA-Regeldateien |
📂 Projektarchitektur
forensics-mcp-framework/
├── pyproject.toml
├── .env.example
├── README.md
├── evidence/ # Evidence locker & chain of custody ledger
│ ├── suspect_photo.jpg
│ ├── eicar_test.com
│ └── chain_of_custody.jsonl
└── src/
├── server.py # Master FastMCP bootstrap & dynamic assembler
├── core/
│ ├── discovery.py # Host & container capability scanner
│ ├── custody.py # Tamper-evident append-only chain of custody
│ └── health.py # System diagnostics & health reporter
├── tools/
│ ├── metadata.py # ExifTool & MIME mismatch detector
│ ├── strings_ioc.py # String & IOC scanner (IP, URL, Base64, shell)
│ ├── threat_intel.py # Offline/online threat intelligence
│ ├── memory_vol.py # Volatility 3 memory analysis engine
│ └── dynamic_cli.py # CLI wrappers (binwalk, tshark, objdump, gdb)
├── resources/
│ └── system_resources.py# MCP Resources
└── prompts/
└── triage_prompts.py # Structured DFIR workflowsAvailable Tools
5 toolscheck_threat_intelB
Queries threat intelligence databases (with safe offline fixture fallback) for a file hash.
Inputs: file_hash (required), case_id. Returns: result
extract_metadataB
Extracts file metadata, computes cryptographic hashes (MD5, SHA-1, SHA-256, SHA-512), and detects MIME-type masquerading.
Inputs: file_path (required), case_id. Returns: result
extract_stringsC
Extracts printable ASCII & Unicode strings from an evidence artifact.
Inputs: file_path (required), case_id, min_length, max_results, +1 more. Returns: result
scan_iocsC
Scans an evidence artifact for Indicators of Compromise: IPs, C2 URLs, email addresses, suspicious commands, and Base64 payloads.
Inputs: file_path (required), case_id. Returns: result
system_health_checkA
Inspects real-time host forensic capability readiness, storage, and chain-of-custody status.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct forensic task: system readiness, metadata extraction, string extraction, IOC scanning, and threat intel lookup. There is no functional overlap, and the descriptions clearly delineate their purposes.
All tool names follow a consistent verb_noun pattern (e.g., system_health_check, extract_metadata, scan_iocs), using snake_case throughout. The naming is predictable and aligns with forensic terminology.
Five tools is appropriate for a forensic server covering host readiness, file analysis, and threat detection. Each tool serves a necessary function without redundancy or gaps in the core workflow.
The toolset covers essential forensic steps: health check, metadata extraction, string extraction, IOC scanning, and threat intel. A minor gap is the absence of a tool for parsing specific artifact types (e.g., registry hives or logs), but the set is sufficient for basic evidence triage.
Maintenance
Related MCP Connectors
Discover, invoke, and verify ForceDream agents with cryptographic proofs. 14 local, 21 hosted tools.
34 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Agent tools for discovery, payment safety, data extraction, and DeFi.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interface with Velociraptor for digital forensics and incident response tasks, including file/memory scans, remediation actions, and artifact collection across multiple operating systems.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables autonomous digital forensics and incident response through 21 typed forensic tools covering disk, memory, registry, network, timeline, carving, and patterns, integrated with AI-driven reasoning and self-correction.MIT
- AlicenseNot gradedqualityBmaintenanceEnables autonomous digital forensics and incident response by wrapping SIFT Workstation tools as MCP tools and orchestrating a multi-agent AI pipeline for evidence analysis and remediation planning.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to analyze memory dumps for forensic investigation, leveraging a fast Rust engine and full Volatility3 plugin coverage via the Model Context Protocol.1MIT