Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by zebbern • Uncategorized
An MCP server enabling AI assistants to execute Kali Linux penetration testing tools via a standardized API.
Perform automated penetration testing using Kali Linux tools.
Integrate security tool execution into AI-assisted development environments.
Manage VPNs, network pivoting, and Active Directory enumeration during security assessments.
Zebbern Kali MCP Server provides a comprehensive Model Context Protocol server for Kali Linux, allowing AI assistants like GitHub Copilot to run over 145 penetration testing tool functions and 22 external tools through a REST API. It supports VPN management, CTF platform integration, browser automation, Active Directory tools, network pivoting, and session management, streamlining security testing workflows. The server can be deployed via Docker or a Kali VM, facilitating seamless integration with development environments such as VS Code.
Execute ANY command on the Kali server without restrictions. Full root access, no timeout limits (default 1 hour). Args: command: The command to execute (can be any shell command, pipes, chains, etc.) timeout: Timeout in seconds (default: 3600 = 1 hour) cwd: Optional working directory for the command background: If True, run fire-and-forget — returns immediately with a task_id Returns: Command output with stdout, stderr, return_code, execution_time. When background=True, returns immediately with a task_id instead.
Execute a command with real-time streaming output via SSE (text/event-stream). Posts to api/command with streaming=True. Useful for long-running commands like nmap, nuclei, fuzzing. Args: command: The command to execute timeout: Timeout in seconds (default: 3600 = 1 hour) Returns: Streaming output collected in real-time with all events
Check the health status of the Kali API server. Returns: Server health information
Get comprehensive network information for the Kali Linux system. Returns: Network information including interfaces, IP addresses, routing table, etc.
Send text input to any active interactive session (msfconsole, SSH, mysql, python REPL, shell, etc.). This is a generic primitive that works with ANY session type managed by the backend — it is not limited to Metasploit. Use this together with read_output() to have a full interactive conversation with a long-running process: 1. Start a session (e.g. via msf_session_create or zebbern_exec with background=True) 2. send_input(session_id, "some command\n") 3. read_output(session_id) to collect the response Args: session_id: The session identifier returned when the session was created. input_text: The text to send to the session's stdin. Include a trailing newline (\n) if the target process expects one. session_type: Hint for the backend on how to handle the session. 'auto' (default) lets the backend detect the type. Other values: 'msfconsole', 'ssh', 'shell', 'mysql', 'python'. Returns: dict with at minimum: - success (bool): whether the input was accepted - session_id (str): echo of the session targeted - error (str, optional): present only on failure
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.