一个演示服务器,它通过与Mythic C2框架接口,允许大型语言模型自主执行渗透测试任务。
security-and-iamos-automationdeveloper-tools
464 查看 · 2026-07-07 更新
简介
一个演示服务器,它通过与Mythic C2框架接口,允许大型语言模型自主执行渗透测试任务。
简介
一个演示服务器,它通过与Mythic C2框架接口,允许大型语言模型自主执行渗透测试任务。
Mythic MCP
一个用于Mythic的快速MCP演示,允许LLMs代表我们进行渗透测试!
要求
- uv
- python3
- Claude Desktop(或其他MCP客户端)
使用Claude Desktop
要使用Claude Desktop部署此MCP服务器,您需要编辑您的claude_desktop_config.json文件以添加以下内容:
{ "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" ] } } }
完成之后,启动Claude Desktop。有一些示例提示展示了如何给LLM分配任务,但实际上任何类似的内容都可以工作,例如:
You are an automated pentester, tasked with emulating a specific threat actor. The threat actor is APT31. Your objective is: Add a flag to C:\win.txt on DC01. Perform any required steps to meet the objective, using only techniques documented by the threat actor.
服务配置
[{'mcpServers': {'mythic_mcp': {'args': ['--directory', '/full/path/to/mythic_mcp/', 'run', 'main.py', 'mythic_admin', 'mythic_admin_password', 'localhost', '7443'], 'command': '/Users/xpn/.local/bin/uv'}}}]
来源
- 来源:github
- 链接:https://github.com/xpn/mythic_mcp