systems-manager
System-Manager will update your system and install/upgrade applications. Supports Agentic AI through MCP Server
claude mcp add --transport stdio knuckles-team-systems-manager python -m systems_manager
How to use
Systems-Manager is an MCP server that exposes a versatile set of system administration capabilities via the MCP (Model Context Protocol) interface. It provides tools for installing and updating applications across multiple operating systems, managing Windows features, installing Nerd Fonts, gathering detailed OS and hardware statistics, and running elevated shell commands when needed. The server is designed to integrate with AI agents and automation systems through MCP over stdio or HTTP, enabling orchestrated system management in mixed environments. You can access the MCP tools such as install_applications, update, clean, optimize, install_python_modules, install_fonts, get_os_stats, get_hardware_stats, list_windows_features, enable_windows_features, disable_windows_features, and run_command to perform common maintenance tasks and gather insights from the target hosts.
How to install
Prerequisites:
- Python 3.8+ (recommended)
- pip (comes with Python)
- Optional: a virtual environment tool (venv, virtualenv)
- Install from PyPI Run:
pip install systems-manager
- Run the MCP server The module exposes the MCP server entry point. Start the server with:
python -m systems_manager
-
Verify the server is running Open the MCP URL or connect via your MCP client to ensure the server is reachable.
-
Optional: Run from source If you prefer to install from source, clone the repo and install in editable mode:
git clone https://github.com/Knuckles-Team/systems-manager.git
cd systems-manager
pip install -e .
- Environment configuration (optional)
- ENABLE_WEB_UI: Set to a truthy value to enable the Pydantic AI Web UI (e.g., export ENABLE_WEB_UI=1)
- LOG_FILE: Path to a log file if you want persistent logs (default: systems_manager.log in the script directory)
Notes:
- The package name on PyPI is systems-manager and the Python module is typically systems_manager. If you installed via a package manager or container, ensure the module name matches your installation.
- For production deployments, consider running behind a process manager and securing MCP transport (HTTP/stdio) according to your security requirements.
Additional notes
Tips and common considerations:
- Use ENABLE_WEB_UI to enable the web UI for interactive management and AI-assisted operations. Ensure proper authentication if exposing the UI publicly.
- The MCP supports multiple transport methods (stdio, http, sse). Choose the transport that best fits your environment and security posture.
- When running Windows-specific features, ensure the host is Windows or supports Windows feature management. Windows-only commands will be no-ops on non-Windows platforms.
- For Python-based setups, virtual environments are recommended to isolate dependencies.
- If you encounter permission issues running elevated shell commands (run_command), run the server with appropriate privileges or adjust your OS policies accordingly.
Related MCP Servers
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
mcp-yfinance
Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp
servicenow-api
ServiceNow MCP Server and API Wrapper
muxi
An extensible AI agents framework
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools