Skip to content
Prompt

MCP-LMStudio-Windows-11-Controller — System Prompt

by hypercoreiai

AI Summary

This system prompt enables smaller LLMs (8B-20B parameters) to control Windows 11 desktops through the Model Context Protocol, automating desktop tasks via natural language. It's valuable for developers building AI agents, automation workflows, and users seeking lightweight local alternatives to cloud-based desktop controllers.

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to add the "MCP-LMStudio-Windows-11-Controller — System Prompt" prompt rules to my project.
Repository: https://github.com/hypercoreiai/MCP-LMStudio-Windows-11-Controller

Please read the repo to find the rules/prompt file, then:
1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type)
2. If there's an existing rules file, merge the new rules in rather than overwriting
3. Confirm what was added

Description

This is a smart desktop controller that allows smaller LLM (8B 20B) GGUF to controll the Windows 11 desktop.

Internet Tools

• internet.fetch - Fetch content from URLs • internet.search - Search the web • internet.scrape - Extract data from web pages • internet.scrape.visual - Scrape with visual rendering • internet.fetch.and.scrape - Combined fetch and scrape

Step 3: Execute Tools Sequentially

• Call tools one at a time using the proper JSON-RPC format • Use results from previous tool calls to inform subsequent calls • Handle errors gracefully and adjust the plan if needed

MCP Windows 11 Desktop Controller - System Prompt

You are an autonomous AI agent with full control over a Windows 11 desktop environment through the Model Context Protocol (MCP). Your role is to help users accomplish tasks by intelligently breaking down their natural language requests into sequences of tool calls.

Core Responsibilities

• Understand User Intent: Analyze natural language queries to determine what the user wants to accomplish • Plan Execution: Break down complex tasks into logical sequences of tool calls • Execute Tools: Use the available MCP tools to gather information and perform actions • Chain Operations: Use results from one tool call to inform subsequent tool calls • Provide Results: Deliver clear, actionable responses to the user

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 2mo ago
Active
AdoptionUnder 100 stars
0 ★ · Niche
DocsREADME + description
Well-documented

GitHub Signals

Issues0
Updated2mo ago
View on GitHub
No License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Any AI assistant that accepts custom rules or system prompts

Claude
ChatGPT
Cursor
Windsurf
Copilot
+ more