Windows Management MCP Server

Windows Management MCP Server

A Python-based MCP server for local Windows diagnostics, task management, cleanup, hardware inspection, security checks, and administrative workflows.

Category
Visit Server

README

Windows Management MCP Server

<!-- mcp-name: io.github.ahmedlaminou/windows-mcp-server -->

Windows Management MCP Server is a Python-based Model Context Protocol server for local Windows diagnostics, task management, cleanup, hardware inspection, security checks, and administrative workflows.

It exposes 96 tools over stdio and is designed for local assistants such as Claude Desktop, Cursor, VS Code extension hosts, and other MCP-compatible clients.

Important: This server runs with the privileges of the user account that starts it. Several tools can change system state, delete files, edit the Registry, manage services, install updates, or execute PowerShell. Use the read-only and dry-run tools first, and only enable destructive actions after reviewing the target paths and commands.

What It Can Do

  • Task manager: CPU, GPU, memory, disk usage, top processes, process trees, process details, suspend/resume/kill.
  • Storage cleanup: disk usage, largest folders/files, duplicate detection, old files, media discovery, Recycle Bin deletion, temp cleanup.
  • Hardware and drivers: GPU details, NVIDIA nvidia-smi probes, display configuration, installed drivers, problem devices, driver update candidates.
  • Windows security: Defender status/scans, firewall rules, BitLocker, Secure Boot, UAC, Windows Update status.
  • System administration: services, startup apps, scheduled tasks, event logs, crash diagnostics, restore points.
  • Network diagnostics: interfaces, active sockets, listening ports, firewall correlation, ping latency.
  • Developer environment: Python/Node discovery, environment variables, common dev ports.
  • Shell helpers: Explorer open/select, screenshots, clipboard, visible windows.
  • Peripherals and virtualization: printers, print queues, audio, Bluetooth, WSL, Hyper-V, optional Windows features.

For the complete tool catalog, see docs/TOOLS.md.

Requirements

  • Windows 10/11 or Windows Server with PowerShell available.
  • Python 3.10 or newer.
  • Some tools require Administrator privileges or Windows features/modules that may not be installed on every machine.
  • Optional vendor data, such as NVIDIA GPU telemetry, requires vendor tools like nvidia-smi on PATH.

Installation

From PyPI:

pip install windows-management-mcp-server

Create a virtual environment and install the package in editable mode:

python -m venv venv
.\venv\Scripts\Activate.ps1
pip install -e .

Both install paths register the windows-mcp-server command in the active environment.

MCP Client Configuration

For clients that can launch a stdio MCP server, use:

{
  "mcpServers": {
    "windows-management": {
      "command": "windows-mcp-server",
      "args": []
    }
  }
}

If the command is not on PATH, point directly at the local virtual environment:

{
  "mcpServers": {
    "windows-management": {
      "command": "C:\\path\\to\\WindowsMCPServer\\venv\\Scripts\\python.exe",
      "args": ["-m", "windows_mcp_server.server"],
      "env": {
        "PYTHONPATH": "C:\\path\\to\\WindowsMCPServer"
      }
    }
  }
}

Running Locally

windows-mcp-server

Or:

python -m windows_mcp_server.server

The server uses stdio transport and is normally launched by an MCP client rather than run interactively.

VS Code Extension

The vscode-extension/ folder contains a small VS Code extension that launches this MCP server from the repo-local virtual environment first, then falls back to a global windows-mcp-server.

cd vscode-extension
npm install
npm run compile

Open vscode-extension/ in VS Code and press F5 to start an Extension Development Host.

Safety Model

Tools are intentionally mixed across read-only, safer mutation, and sharp mutation categories.

  • Prefer report tools first: disk_cleanup_report, get_security_status, get_windows_update_status, list_scheduled_tasks, get_process_details.
  • Prefer safe deletion: safe_delete_to_recycle_bin, safe_delete_many_to_recycle_bin, safe_delete_by_pattern with dry_run=true.
  • Treat these as sharp tools: execute_powershell, Registry writes/deletes, permanent file deletion, service changes, update installation, process termination, restore point creation.

See docs/SECURITY_MODEL.md before exposing this server to an assistant you do not fully trust.

Development

Compile-check the Python package:

.\venv\Scripts\python.exe -m compileall windows_mcp_server

Check the registered tool count:

.\venv\Scripts\python.exe -c "from windows_mcp_server.registry import register_all_tools, registered_tools; Dummy=type('Dummy',(),{'tool':lambda self: (lambda f:f)}); register_all_tools(Dummy()); print(len(registered_tools))"

Compile the VS Code extension:

cd vscode-extension
npm run compile

Repository Structure

windows_mcp_server/        Python MCP server package
windows_mcp_server/tools/  Tool modules grouped by Windows domain
vscode-extension/          Optional VS Code extension wrapper
docs/                      Tool catalog, security model, publishing guide
server.json                MCP Registry metadata
pyproject.toml             Python package metadata

Publishing

This repository includes server.json for the MCP Registry and PyPI-compatible package metadata.

See docs/PUBLISHING.md for the full GitHub, PyPI, and MCP Registry release flow.

License

MIT. See LICENSE.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured