Post-Exploitation tmux MCP Server
Exposes tmux features to AI agents for managing sessions, windows, and panes with built-in command execution. It includes comprehensive guardrails to prevent destructive system operations, file deletions, and unauthorized network changes.
README
🖥️ Post-Exploitation tmux MCP Server
A MCP server that exposes essential tmux features as MCP tools — giving AI agents a terminal multiplexer for post-exploitation operations, with built-in guardrails that block destructive commands.
✨ Tools (14)
| Category | Tools | Description |
|---|---|---|
| Sessions | 3 | Create, list, kill |
| Windows | 3 | Create, list, kill |
| Panes | 3 | Split, list, kill |
| Command Execution | 3 | execute_command, send_keys, capture_pane — all guarded |
| Utility | 2 | validate_command_safety, kill_server |
🛡️ Guardrails
Every command sent through execute_command or send_keys is validated before execution. The guardrails block:
- File destruction —
rm -rf /,shred,wipefs - Disk operations —
mkfs,dd if=,fdisk,parted - Fork bombs —
:(){ :|:& };: - System shutdown —
shutdown,reboot,halt,init 0/6 - Critical process killing —
kill -9 1,killall -9 - Permission bombs —
chmod -R 777 / - Dangerous redirects —
> /etc/passwd,> /etc/shadow - Network destruction —
iptables -F - Log tampering —
> /var/log/,history -c - Obfuscated execution —
curl ... | sh,base64 -d | sh
📦 Installation
cd Post-Exploitation
pip install -r requirements.txt
Prerequisite: tmux must be installed on the target machine.
🚀 Usage
Run the MCP server
python server.py
Test with the interactive client
python client.py
The client connects to server.py via stdio, lists available tools, and gives you an interactive REPL to call them.
Connect from an MCP client (e.g. AI agent)
{
"mcpServers": {
"post-exploitation-tmux": {
"command": "python3",
"args": ["path/to/Post-Exploitation/server.py"]
}
}
}
🔧 Tool Reference
Sessions
| Tool | Description |
|---|---|
create_session(name, window_name?) |
Create a new detached session |
list_sessions() |
List all sessions |
kill_session(name) |
Destroy a session |
Windows
| Tool | Description |
|---|---|
create_window(session, name?) |
Create a new window |
list_windows(session) |
List windows |
kill_window(session, index) |
Kill a window |
Panes
| Tool | Description |
|---|---|
split_pane(session, window, direction?) |
Split pane vertically/horizontally |
list_panes(session, window) |
List panes with command & PID |
kill_pane(session, window, pane) |
Kill a pane |
Command Execution (Guarded)
| Tool | Description |
|---|---|
execute_command(session, window, pane, command) |
Run a command (guardrail-checked) |
send_keys(session, window, pane, keys, press_enter?) |
Send keystrokes (guarded if Enter) |
capture_pane(session, window, pane, start?, end?) |
Read pane output (trailing blanks stripped) |
Utility
| Tool | Description |
|---|---|
validate_command_safety(command) |
Pre-check a command without executing |
kill_server() |
Kill the tmux server (destroys all sessions) |
📂 Project Structure
Post-Exploitation/
├── server.py # FastMCP server — 14 tools
├── tmux_wrapper.py # Thin Python wrapper around tmux CLI
├── guardrails.py # Command validation & safety checks
├── client.py # Interactive MCP test client
├── test_guardrails.py # Guardrails unit tests
├── requirements.txt # Python dependencies
└── README.md # This file
🧪 Testing
Run guardrail tests
python test_guardrails.py
Test MCP tools interactively
python client.py
⚠️ Disclaimer
This tool is intended for authorized penetration testing and security research only. Unauthorized use against systems you do not own or have explicit permission to test is illegal.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。