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., "@Windows Server MCP what's the current CPU and memory usage?"
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.
Windows Server MCP is a local Model Context Protocol server for read-only Windows observability. It exposes CPU, memory, storage, service, and health tools through FastMCP.
Current version: 1.0.0.
Tool | Purpose |
| Server health, Python runtime, and platform details. |
| Normalized compatibility connectivity check. |
| CPU counts, utilization, frequency, load, stats, and times. |
| Virtual memory and swap details with byte-based values. |
| Disk partitions, byte usage totals, and disk I/O counters. |
| Windows services with optional filters and compact defaults. |
| Detailed information for one Windows service. |
All tools return a consistent shape:
{
"data": {},
"errors": [],
"meta": {
"timestamp": "2026-08-17T00:00:00+00:00",
"source": "psutil",
"tool": "tool_name"
}
}Related MCP server: Windows MCP Server
Windows
Python 3.10+
python -m venv .venv
.\.venv\Scripts\activate
pip install -r requirements.txt.\.venv\Scripts\activate
python main.pyThe server runs at:
http://127.0.0.1:8080/mcpStart the server, then run:
npx @modelcontextprotocol/inspector --server-url http://127.0.0.1:8080/mcp --transport httpYou can also use CLI mode:
npx @modelcontextprotocol/inspector --cli http://127.0.0.1:8080/mcp --transport http --method tools/list.\.venv\Scripts\python.exe -m unittest discover -s tests -vCall cpu_info with a shorter sample interval:
{
"interval_seconds": 0.5
}List only running services:
{
"status": "running"
}List services with detailed fields:
{
"include_details": true,
"limit": 25
}Include all disk partitions:
{
"all_partitions": true
}MIT
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TechGOELogy/windows-server-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
