SkillAgentSearch skills...

mcp-os-native-automation

High-Trust Open-Core framework for Windows AI Agents. Crushes latency to 3.9ms, enables background UIA invocation, and protects enterprise RPA workflows.

Install / Use

claude mcp add a92070888-dev -- npx -y github:a92070888-dev/mcp-os-native-automation

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

78/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop
Cursor

Our assessment of mcp-os-native-automation

mcp-os-native-automation scores 78/100 on our quality scale, 1743rd of 2,166 Automation skills we index.

Its MCP Server is 5.3 KB long, well organised into 27 sections with 10 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so mcp-os-native-automation is actively maintained.
  • Our last check on 2026-09-20 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

mcp-os-native-automation compared with similar skills

All 4 of these similar skills score higher than mcp-os-native-automation; compare them before choosing.

SkillScoreStarsUpdatedFormat
mcp-os-native-automation (this skill)by a92070888-dev7833mo agoMCP Server
Agent-Reachby Panniantong10086.1k13d agoCLAUDE.md
headroomby headroomlabs-ai10074.1ktodayCLAUDE.md
rufloby ruvnet10073.5ktodayCLAUDE.md
CowAgentby zhayujie10047.2ktodayCLAUDE.md

Frequently asked questions

How do I install mcp-os-native-automation?
Run claude mcp add a92070888-dev -- npx -y github:a92070888-dev/mcp-os-native-automation. The install tabs above show the steps for each supported agent.
Which AI agents does mcp-os-native-automation work with?
It is written for Claude Code, Claude Desktop and Cursor, as a MCP Server file. Other agents that read the same format can often use it too.
Is mcp-os-native-automation safe to use?
It is MIT-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is mcp-os-native-automation still maintained?
The repository was last updated about 3 months ago, so mcp-os-native-automation is actively maintained.

🏆 Front-End Operation Master (FEOM)

The Ultimate Front-End OS Engine for AI Agents. 0 Vision Tokens. 733× Faster. 100% Deterministic.

FEOM is a production-grade front-end operation architecture for Windows AI Agents. This repository contains the Open-Core Edition, allowing developers to test and verify real-time structural OS routing (achieving ~8ms background UIA invocation), completely eliminating VLM vision token costs.

📊 Feature Matrix: Open-Core vs Pro/Enterprise

| Feature | 🟡 Open-Core (This Repo) | 🟢 FEOM Pro / Enterprise | |:---|---:|:---:| | MCP Server Framework | ✅ Included | ✅ Included | | UIA Tree Structural Read | ✅ Included (~75ms) | 🚀 Predictive Async Cache (<1ms) | | Win32 SendInput Click | 🟢 Standard (~3.96ms) | ⚡ Zero-Alloc UltraClick (<1.0ms) | | Background UIA Invoke | 🟢 Basic (~8ms) | ⚡ Win32 PostMessage (~1ms) | | Multi-Monitor High DPI | ❌ Static Coords Only | ✅ Dynamic Scaling Matrix | | Taskbar Push Auto-Recovery | ❌ Fixed Offsets | ✅ Icon Vector Tracking | | Input Pipeline Optimization | ❌ Raw Character Streams | ✅ Clipboard Parallel (-71%) |


🥇 The Three Iron Rules of Production Automation

1. Unique Truth: Front-End Demonstration Over Everything

Always show, then report. Every sequence must execute visibly in the foreground.

2. Safety First: Pre-Action Focus Defending

Never click blindly. Structural state verification is forced prior to any input.

3. App Termination Rule: Strict Alt+F4 Ban

Alt+F4 blindly kills whatever window has focus — frequently closing the orchestration engine itself.


🚀 Hybrid Terminal+MCP Extreme Mode

| Execution Stage | Traditional MCP Agent | FEOM Hybrid Mode | Time Saved | |:---|:---:|:---:|:---:| | App Bootup | ~3.0s (UI traversal) | 0.01s | 99.6% | | Form Input | ~5.0s (Vision Loop) | 1.2s | 76.0% | | Close & Verify | ~4.0s (Screenshot) | 2.0s | 50.0% | | Total End-to-End | ~12.0s | ~3.21s | 73.2% Faster |

# Verify instant boot:
terminal("start calc")

Hardware Requirements (Killer Feature)

| Requirement | Traditional VLM | FEOM Open-Core | |:------------|:-------------:|:-------------:| | GPU | RTX 3060+ required | None - any CPU works | | RAM | 16GB+ | 4GB | | Network | Required (API per click) | Zero - fully local | | Cost/op | $0.01-$0.05 (vision tokens) | $0 | | Display | Yes (needs screenshot) | No - works headless | | Hardware cost | $1,000+ gaming PC | $50 used Dell | | Annual license | $15K+ (RPA) | $0 (Open-Core) |

Deterministic vs Probabilistic

| | VLM Screenshot | FEOM OS-Native | |:---|:-------------:|:-------------:| | Output | Coordinate guessing | AutomationID targeting | | Repeatability | Different each time | 100% identical | | DPI scaling | Coordinates drift | UIA auto-maps | | Background | Cannot work | Works minimized | | Production-ready | Demo only | Production grade |

💼 Commercial Licensing

| Tier | Product | Price | |:---|:---|---:| | 1 | Turbo-MCP Plugin (anti-crash + DPI matrix) | $14.99/mo | | 2 | AI-SaaS Task Force (legacy ERP/CRM migration) | Custom | | 3 | Enterprise Consulting (stability + multi-monitor audit) | $3K-$10K | | 4 | Hermes-Split-OS SDK (parallel multi-agent framework) | License |

Inquiries: Open B2B Ticket or a92070888@gmail.com

3-Line Quick Start

pip install pywinauto pywin32 mcp
python server.py

Then add to MCP client config:

{
  "mcpServers": {
    "feom": {
      "command": "python",
      "args": ["path/to/server.py"]
    }
  }
}

No GPU. No cloud API. No Docker. Any Windows PC.

Tools (Open-Core)

| Tool | Description | Latency | |:-----|:------------|:------:| | feom_click | Click at screen coords via SendInput | ~4ms | | feom_uia_invoke | Invoke UIA element by AutomationID | ~8ms | | feom_launch | Launch app via terminal pipe | ~0.01s | | feom_list_windows | List all visible windows | ~75ms |

Quick Start

pip install pywinauto pywin32 mcp python server.py


Installation

Option 1: pip install (recommended)

pip install feom-mcp
python -m feom.server

Option 2: Clone and run

git clone https://github.com/a92070888-dev/mcp-os-native-automation.git
cd mcp-os-native-automation
pip install -r requirements.txt
python server.py

Option 3: UVX (MCP client auto-discovery)

{
  "mcpServers": {
    "feom": {
      "command": "uvx",
      "args": ["feom-mcp"]
    }
  }
}

MCP Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "feom": {
      "command": "python",
      "args": ["path/to/server.py"]
    }
  }
}

Cursor IDE

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "feom": {
      "command": "python",
      "args": ["path/to/server.py"]
    }
  }
}

Any MCP Client (stdio)

{
  "mcpServers": {
    "feom": {
      "command": "uvx",
      "args": ["feom-mcp"]
    }
  }
}

Verify Installation

python server.py
# Server starts on stdio. Expected output:
# FEOM MCP server ready

Requirements

  • OS: Windows 10/11 only
  • Python: 3.10+
  • No GPU required
  • No API keys required
  • No Docker required

3-Line Quick Start

Related Skills

View on GitHub
GitHub Stars3
CategoryAutomation
Updated2mo ago
Forks0

Languages

Python

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low