What are the requirements for running Mythic MCP?
You need `uv`, Python 3, and an MCP client such as Claude Desktop.
@xpn
基本情報
A simple POC to expose Mythic as a MCP server
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": {
"mythic_mcp": {
"command": "/Users/xpn/.local/bin/uv",
"args": [
"--directory",
"/full/path/to/mythic_mcp/",
"run",
"main.py",
"mythic_admin",
"mythic_admin_password",
"localhost",
"7443"
]
}
}
}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。
Mythic MCP is a demo MCP server that integrates LLMs with the Mythic command-and-control framework, allowing LLMs to perform automated penetration testing on behalf of the user. It is intended for pentesters and security researchers using MCP-compatible clients like Claude Desktop.
Install uv and Python 3, then edit your claude_desktop_config.json to add a server entry pointing to the Mythic MCP directory with command, args (including Mythic admin credentials, host, and port), and launch Claude Desktop. Sample prompts are provided to task the LLM with threat‑actor emulation.
uv and Python 3 for easy deploymentYou need `uv`, Python 3, and an MCP client such as Claude Desktop.
Edit `claude_desktop_config.json` to add an `mcpServers` entry with the `command` set to the `uv` binary, and `args` including the full path to the Mythic MCP directory, your Mythic admin username, password, host, and port number (e.g., `7443`).
Yes, the README lists “Claude Desktop (or other MCP Client)” as a requirement, indicating client flexibility.
The server expects a Mythic admin username and password to be passed as command‑line arguments, followed by the host and port of the Mythic instance.
The README provides a sample prompt that tasks the LLM as an automated pentester emulating a specific threat actor (e.g., APT31) with a concrete objective, such as adding a flag to a file on a remote host.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

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.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
A curated list of references for MLOps

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
コメント