Provides unrestricted access to Kali Linux tools for penetration testing, CTF challenges, and offensive security automation, including command execution, long-running async jobs, and file operations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
RETRO MCP KALI is a fully unrestricted MCP (Model Context Protocol) server that exposes all Kali Linux tools over Streamable HTTP. Designed for AI‑powered penetration testing, CTF challenges, and offensive security automation – with no safety filters, no restrictions, and full root power.
⚠️ WARNING – This server gives unrestricted root access to your Kali machine.
There are no safety filters – you can run any command, including destructive ones.
USE ONLY IN ISOLATED, CONTROLLED ENVIRONMENTS.
The author is NOT responsible for any damage or legal consequences.
Related MCP server: K-MCP: Kali Model Context Protocol Server
RETRO MCP KALI is built to work seamlessly with Rikkhahub – a powerful AI chat client for Android that supports MCP servers over Streamable HTTP.
Open Rikkhahub on your Android device.
Go to Settings → MCP Servers.
Add a new server with:
Transport Type: Streamable HTTP
Server URL: http://<YOUR_KALI_IP>:8000/mcp
Enable: ON
Save and start chatting with your AI assistant – it now has full Kali Linux access!
✅ Complete Tool Access – All Kali tools exposed as MCP tools.
🚫 No Restrictions – Execute any command, install any package, run any exploit.
⏳ Async Jobs – Run long‑running scans in the background and poll for results.
📁 File Operations – Upload, download, list, and delete files directly.
🌐 Streamable HTTP – Works with Rikkhahub, Claude Desktop, 5ire, and any MCP client.
⚡ One‑Command Setup – Install and run with a single command: retro-mcp-kali.
curl -sSL https://raw.githubusercontent.com/alongbarbasumatary/RETRO-MCP-KALI/main/setup.sh | sudo bashThis server cannot be deployed
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets.
Connect AI assistants to authorized Windows and macOS devices for files, commands, and management.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
