SystemKernelMCP
Provides tools for managing Docker containers, images, and compose stacks, including listing containers, viewing logs, executing commands, and composing up.
Enables Git operations such as checking status, cloning repositories, committing changes, and pushing to remotes.
Allows interaction with GitHub repositories, pull requests, and issues via the gh CLI.
Facilitates Kubernetes cluster management with tools for listing pods, viewing logs, applying configurations, and deleting resources.
Enables chat interactions with local LLMs via Ollama.
Provides chat completion functionality using OpenAI's API.
Manages QEMU virtual machines, including listing VMs.
Allows execution of Redis commands via redis-cli (optional).
Supports Terraform infrastructure as code operations, such as planning.
Enables vulnerability scanning using Trivy.
Provides tools for listing VirtualBox virtual machines.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SystemKernelMCPList all running Docker containers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SystemKernelMCP
180+ tools for full system control: terminal, Git, Docker, Kubernetes, VMs, BIOS, kernel, cybersec (50+ pentesting tools), AI, cloud. Works with Cursor, Claude Desktop, Windsurf, and any MCP client.
What is this?
SystemKernelMCP is an MCP (Model Context Protocol) server. It gives your AI assistant (Cursor, Claude, etc.) 180+ tools to control your system: run terminal commands, manage Docker, pentest (nmap, nuclei, sqlmap, etc.), read files, and more.
You do NOT run it yourself. Your AI client (Cursor, Claude) starts it automatically when you ask for a tool.
Related MCP server: allcanuse-mcp
Quick Start (3 steps)
Step 1: Install
# Create virtual environment
python -m venv venv
# Activate (pick one for your terminal)
# Windows CMD: .\venv\Scripts\activate
# Windows Git Bash: source venv/Scripts/activate
# Mac/Linux: source venv/bin/activate
# Install MCP
pip install -r requirements.txt
# or: pip install mcpStep 2: Add to your AI client
For Cursor: This project already has .cursor/mcp.json. Just open the folder in Cursor.
For Claude Desktop: Add to claude_desktop_config.json:
{
"mcpServers": {
"SystemKernelMCP": {
"command": "python",
"args": ["C:\\full\\path\\to\\MCP SERVER\\system_mcp.py"],
"cwd": "C:\\full\\path\\to\\MCP SERVER"
}
}
}For other clients: Add the same config to your client's MCP settings.
Step 3: Restart and use
Restart Cursor (or your AI client)
Enable SystemKernelMCP in Settings → MCP
In chat, ask: "Run get_os_info" or "Ping google.com"
Approve the tool when prompted
Health check: Call health_check or get_os_info. If you get a response, it's working.
Important: Do NOT run manually
python system_mcp.py # ❌ Wrong - will show a message and exitThis is a stdio server. It talks over stdin/stdout. Your AI client starts it automatically. Running it in a terminal does nothing useful.
Supported clients
Client | Config location |
Cursor |
|
Claude Desktop |
|
Windsurf | Similar to Cursor |
Custom | Any MCP client that supports stdio |
Tools (180+)
Category | Examples |
Terminal |
|
OS |
|
Files |
|
Network |
|
Docker |
|
Kubernetes |
|
Git |
|
GitHub |
|
VMs |
|
BIOS/Kernel |
|
Cybersec |
|
AI |
|
Cloud |
|
Dev |
|
Full list: index.html
Troubleshooting
Problem | Fix |
"No such file" in Cursor | Use absolute path in |
MCP not in tools list | Restart Cursor, enable in Settings → MCP |
"Invalid JSON" when running manually | Normal. Don't run manually. Use from Cursor. |
venv activate fails in Git Bash | Use |
Requirements
Python 3.10+
Optional (for specific tools): docker, kubectl, gh, git, nmap, terraform, aws, gcloud, redis-cli, whois, VirtualBox, VMware, Hyper-V, WSL
Optional (cybersec tools): nmap, rustscan, masscan, gobuster, feroxbuster, ffuf, dirsearch, nuclei, nikto, sqlmap, wpscan, subfinder, amass, httpx, hakrawler, katana, gau, waybackurls, arjun, paramspider, dalfox, wafw00f, fierce, dnsenum, theHarvester, hydra, john, hashcat, enum4linux, smbmap, netexec, autorecon, gdb, radare2, ghidra, binwalk, checksec, volatility, foremost, steghide, exiftool, prowler, trivy, kube-hunter, kube-bench, checkov, terrascan
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/needyamin/system-kernel-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server