Proyecto HTB Agent
@sjimnar
About Proyecto HTB Agent
An AI agent powered by cline.bot designed to solve Capture The Flag (CTF) challenges on a Kali Linux virtual machine via an MCP Server.
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Proyecto HTB Agent?
Proyecto HTB Agent is an AI agent designed for cline.bot that assists in solving Hack The Box (HTB) machines and security CTFs using an MCP server running on Kali Linux. It leverages natural language documentation to define workflows instead of Python code, allowing direct interaction with the MCP server.
How to use Proyecto HTB Agent?
Create a machine folder inside htb-agent/ctf_docs/ with an info.json file containing target_ip, hostname, os, and other fields. Then invoke the agent with a command like "Cline, inicia el agente para la máquina '[machine-name]'". The agent reads info.json, interprets workflow structures from main_agent.py, and uses workflows.md to execute tools via the native use_mcp_tool capability.
Key features of Proyecto HTB Agent
- AI agent for HTB and CTF machine resolution.
- Natural language workflows instead of Python code.
- Uses cline.bot's native MCP capabilities.
- Asynchronous execution for long-running tools.
- Structured phases: environment prep, reconnaissance, exploitation, privilege escalation.
- Requires a configured Kali Linux MCP server.
Use cases of Proyecto HTB Agent
- Automating the reconnaissance and exploitation of Hack The Box machines.
- Performing web enumeration using Gobuster and Nikto.
- Conducting vulnerability scanning with SQLMap.
- Executing brute-force attacks with Hydra.
- Asynchronously running tools to avoid timeouts.
FAQ from Proyecto HTB Agent
How does Proyecto HTB Agent differ from typical CTF automation scripts?
It focuses on natural language documentation and uses cline.bot's native MCP tool execution, avoiding additional abstraction layers.
What are the runtime requirements?
A Kali Linux machine with an accessible MCP server, and cline.bot configured to use that server.
Where does the agent store results?
Within the specific machine's folder under htb-agent/ctf_docs/[machine-name]/, in the info.json file which gets updated as the agent progresses.
What transports and authentication does the server use?
The README specifies the server name "kali-mcp" and URL http://10.196.1.68:5000, but does not detail authentication or transport method beyond HTTP.
Are there any known limitations?
The agent assumes the Kali MCP server is already configured and accessible; no other limitations are mentioned.
Frequently asked questions
How does Proyecto HTB Agent differ from typical CTF automation scripts?
It focuses on natural language documentation and uses cline.bot's native MCP tool execution, avoiding additional abstraction layers.
What are the runtime requirements?
A Kali Linux machine with an accessible MCP server, and cline.bot configured to use that server.
Where does the agent store results?
Within the specific machine's folder under `htb-agent/ctf_docs/[machine-name]/`, in the `info.json` file which gets updated as the agent progresses.
What transports and authentication does the server use?
The README specifies the server name "kali-mcp" and URL `http://10.196.1.68:5000`, but does not detail authentication or transport method beyond HTTP.
Are there any known limitations?
The agent assumes the Kali MCP server is already configured and accessible; no other limitations are mentioned.
Basic information
More AI & Agents MCP servers
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

Competitor Tracker & Co.
Competitor Tracker & Co.Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Comments