ScreenMonitorMCP v2

1# ScreenMonitorMCP v2
2 
3[![Version](https://img.shields.io/badge/version-2.0.7-blue.svg)](https://github.com/inkbytefo/ScreenMonitorMCP/releases/tag/v2.0.7)
4[![PyPI](https://img.shields.io/pypi/v/screenmonitormcp-v2.svg)](https://pypi.org/project/screenmonitormcp-v2/)
5[![Python](https://img.shields.io/pypi/pyversions/screenmonitormcp-v2.svg)](https://pypi.org/project/screenmonitormcp-v2/)
6[![Verified on MseeP](https://mseep.ai/badge.svg)](https://mseep.ai/app/a2dbda0f-f46d-40e1-9c13-0b47eff9df3a)
7[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/inkbytefo-screenmonitormcp-badge.png)](https://mseep.ai/app/inkbytefo-screenmonitormcp)
8A powerful Model Context Protocol (MCP) server that gives AI real-time vision capabilities and enhanced UI intelligence. Transform your AI assistant into a visual powerhouse that can see, analyze, and interact with your screen content.
9 
10## What is ScreenMonitorMCP?
11 
12ScreenMonitorMCP v2 is a revolutionary MCP server that bridges the gap between AI and visual computing. It enables AI assistants to capture screenshots, analyze screen content, and provide intelligent insights about what's happening on your display.
13 
14## Key Features
15 
16- **Real-time Screen Capture**: Instant screenshot capabilities across multiple monitors
17- **AI-Powered Analysis**: Advanced screen content analysis using state-of-the-art vision models
18- **Streaming Support**: Live screen streaming for continuous monitoring
19- **Performance Monitoring**: Built-in system health and performance metrics
20- **Multi-Platform**: Works seamlessly on Windows, macOS, and Linux
21- **Easy Integration**: Simple setup with Claude Desktop and other MCP clients
22 
23## Quick Start
24 
25### Installation
26 
27```bash
28# Install from PyPI
29pip install screenmonitormcp
30 
31# Or install from source
32git clone https://github.com/inkbytefo/screenmonitormcp.git
33cd screenmonitormcp
34pip install -e .
35```
36 
37### Configuration
38 
391. Create a `.env` file with your AI service credentials:
40 
41```env
42OPENAI_API_KEY=your-api-key-here
43OPENAI_MODEL=gpt-4o
44```
45 
462. Add to your Claude Desktop config:
47 
48```json
49{
50  "mcpServers": {
51    "screenmonitormcp-v2": {
52      "command": "python",
53      "args": ["-m", "screenmonitormcp_v2.mcp_main"],
54      "env": {
55        "OPENAI_API_KEY": "your-openai-api-key-here",
56        "OPENAI_BASE_URL": "https://openrouter.ai/api/v1",
57        "OPENAI_MODEL": "qwen/qwen2.5-vl-32b-instruct:free"
58      }
59    }
60  }
61}
62```
63 
643. Restart Claude Desktop and start capturing!
65 
66## Available Tools
67 
68- `capture_screen` - Take screenshots of any monitor
69- `analyze_screen` - AI-powered screen content analysis
70- `analyze_image` - Analyze any image with AI vision
71- `create_stream` - Start live screen streaming
72- `get_performance_metrics` - System health monitoring
73 
74## Use Cases
75 
76- **UI/UX Analysis**: Get AI insights on interface design and usability
77- **Debugging Assistance**: Visual debugging with AI-powered error detection
78- **Content Creation**: Automated screenshot documentation and analysis
79- **Accessibility Testing**: Screen reader and accessibility compliance checking
80- **System Monitoring**: Visual system health and performance tracking
81 
82## Documentation
83 
84For detailed setup instructions and advanced configuration, see our [MCP Setup Guide](MCP_SETUP_GUIDE.md).
85 
86## Requirements
87 
88- Python 3.8+
89- OpenAI API key (or compatible service)
90- MCP-compatible client (Claude Desktop, etc.)
91 
92## Contributing
93 
94We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
95 
96## License
97 
98MIT License - see [LICENSE](LICENSE) for details.
99 
100## Previous Version
101 
102Looking for v1? Check the [v1 branch](https://github.com/inkbytefo/ScreenMonitorMCP/tree/v1) for the previous version.
103 
104---
105 
106**Built with ❤️ by [inkbytefo](https://github.com/inkbytefo)**
107