SystemKernelMCP

SystemKernelMCP

Provides 180+ tools for full system control including terminal, Git, Docker, Kubernetes, VMs, BIOS, kernel, cybersecurity, AI, and cloud, designed to work with MCP clients like Cursor and Claude Desktop.

Category
访问服务器

README

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.

GitHub


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.


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 mcp

Step 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

  1. Restart Cursor (or your AI client)
  2. Enable SystemKernelMCP in Settings → MCP
  3. In chat, ask: "Run get_os_info" or "Ping google.com"
  4. 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 exit

This 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 .cursor/mcp.json (in project)
Claude Desktop claude_desktop_config.json
Windsurf Similar to Cursor
Custom Any MCP client that supports stdio

Tools (180+)

Category Examples
Terminal execute_terminal_command, run_commands
OS get_os_info, get_running_processes, get_services
Files read_file, write_file, list_directory, file_hash, grep_files
Network ping_host, check_port, dns_lookup, http_request, ssl_cert_info
Docker docker_ps, docker_logs, docker_exec, docker_compose_up
Kubernetes k8s_pods, k8s_logs, k8s_apply, k8s_delete
Git git_status, git_clone, git_push, git_commit
GitHub gh_repos, gh_pr_list, gh_issue_list
VMs hyperv_list_vms, virtualbox_list_vms, wsl_run, qemu_list_vms
BIOS/Kernel bios_info, kernel_sysctl_get, kernel_modules_list
Cybersec nmap_scan, port_scan_range, nuclei_scan, gobuster_scan, sqlmap_scan, subfinder_enum, hydra_brute, ghidra_analyze, trivy_scan, cybersec_server_execute
AI openai_chat, ollama_chat
Cloud terraform_plan, aws_cli, gcloud_cli
Dev python_run, venv_create, pip_install

Full list: index.html


Troubleshooting

Problem Fix
"No such file" in Cursor Use absolute path in args and cwd
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 source venv/Scripts/activate

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

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选