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
๐ฅ๏ธ Post-Exploitation tmux MCP Server
A MCP server that exposes essential tmux features as MCP tools โ giving AI agents a terminal multiplexer for post-exploitation operations, with built-in guardrails that block destructive commands.
โจ 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 โ all guarded |
| Utility | 2 | validate_command_safety, kill_server |
๐ก๏ธ Guardrails
Every command sent through execute_command or send_keys is validated before execution. The guardrails block:
- File destruction โ
rm -rf /,shred,wipefs - Disk operations โ
mkfs,dd if=,fdisk,parted - Fork bombs โ
:(){ :|:& };: - System shutdown โ
shutdown,reboot,halt,init 0/6 - Critical process killing โ
kill -9 1,killall -9 - Permission bombs โ
chmod -R 777 / - Dangerous redirects โ
> /etc/passwd,> /etc/shadow - Network destruction โ
iptables -F - Log tampering โ
> /var/log/,history -c - Obfuscated execution โ
curl ... | sh,base64 -d | sh
๐ฆ Installation
cd Post-Exploitation
pip install -r requirements.txt
Prerequisite: tmux must be installed on the target machine.
๐ 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"]
}
}
}
๐ง 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) |
๐ Project Structure
Post-Exploitation/
โโโ server.py # FastMCP server โ 14 tools
โโโ tmux_wrapper.py # Thin Python wrapper around tmux CLI
โโโ guardrails.py # Command validation & safety checks
โโโ client.py # Interactive MCP test client
โโโ test_guardrails.py # Guardrails unit tests
โโโ requirements.txt # Python dependencies
โโโ README.md # This file
๐งช Testing
Run guardrail tests
python test_guardrails.py
Test MCP tools interactively
python client.py
โ ๏ธ 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.