What dependencies are required?
You need Ollama (for AI analysis), Sherlock and Mosint (for OSINT tooling), and a Python virtual environment with the packages in `requirements.txt`. All investigations are run locally.
@cycloarcane
基本情報
MCP servers for automated penetration testing and OSINT.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Hostile-Command-Suite": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Hostile‑Command‑Suite is a terminal‑based OSINT (Open Source Intelligence) investigation framework that combines automated profile scraping, multi‑platform username and email discovery, and local AI analysis via Ollama. It is built for security researchers and intelligence analysts who need a self‑contained, offline‑capable toolchain.
Install Ollama and pull a model (e.g., ollama pull qwen3:8b), then install Sherlock and Mosint. Clone the repository, create a Python virtual environment, and install dependencies. Run python3 HCSO.py --interactive for a guided investigation or pass target data directly on the command line (e.g., python3 HCSO.py "John Smith, @johnsmith123, john@example.com"). Use the --model flag to select a different Ollama model.
You need Ollama (for AI analysis), Sherlock and Mosint (for OSINT tooling), and a Python virtual environment with the packages in `requirements.txt`. All investigations are run locally.
No. All AI analysis happens locally via Ollama. No data leaves your machine, and investigation results are not stored long‑term.
Hostile‑Command‑Suite is released under the PolyForm Noncommercial License 1.0.0, which permits non‑commercial use only.
Yes. Create a new MCP server file in `mcp_tools/`, register it in `MCPToolManager`, and update the agent prompts. The README provides step‑by‑step instructions.
The README emphasizes legal compliance, authorization, and respecting platform rate limits. The system is designed for defensive security and legitimate research only.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Model Context Protocol Servers
Hindsight: Agent Memory That Learns

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
コメント