ScreenMonitorMCP v2

A REVOLUTIONARY Model Context Protocol (MCP) server! Gives AI real-time vision capabilities and enhanced UI intelligence power. This isn't just screen capture - it gives AI the power to truly "see" and understand your digital world!

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "inkbytefo-screenmonitormcp": {
      "command": "python",
      "args": [
        "-m",
        "screenmonitormcp_v2.mcp_main"
      ],
      "env": {
        "OPENAI_MODEL": "qwen/qwen2.5-vl-32b-instruct:free",
        "OPENAI_API_KEY": "your-openai-api-key-here",
        "OPENAI_BASE_URL": "https://openrouter.ai/api/v1"
      }
    }
  }
}

ScreenMonitorMCP v2 is a server that lets an AI assistant capture your screen, analyze visual content in real time, and stream the display for intelligent, UI-aware interactions. It enables you to integrate powerful vision capabilities into your MCP client workflows, turning your AI into a capable visual agent that can see, understand, and respond to your screen content.

How to use

To use ScreenMonitorMCP v2, run the local MCP process and connect your MCP client (such as Claude Desktop) to the provided stdio endpoint. The server exposes commands that let you capture screenshots, analyze screen content with AI models, start live streams, and monitor system health. Configure your client to launch the MCP runner and supply the required environment credentials so your AI services can access the screen content securely.

How to install

Prerequisites: ensure you have Python 3.8+ installed on your system.

# Install from PyPI
pip install screenmonitormcp

# Or install from source
git clone https://github.com/inkbytefo/screenmonitormcp.git
cd screenmonitormcp
pip install -e .

Additional configuration and usage notes

Create a .env file with your AI service credentials and necessary model settings. Then configure your MCP client to launch the server using the Python module as the entry point.

OPENAI_API_KEY=your-openai-api-key-here
OPENAI_MODEL=gpt-4o

Client configuration example

In your Claude Desktop config, add the following MCP server entry to connect to ScreenMonitorMCP v2. This launches the server module directly and passes the required environment variables.

{
  "mcpServers": {
    "screenmonitormcp_v2": {
      "command": "python",
      "args": ["-m", "screenmonitormcp_v2.mcp_main"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here",
        "OPENAI_BASE_URL": "https://openrouter.ai/api/v1",
        "OPENAI_MODEL": "qwen/qwen2.5-vl-32b-instruct:free"
      }
    }
  }
}

Available tools

capture_screen

Take screenshots of any monitor for AI analysis or streaming.

analyze_screen

AI-powered analysis of the current screen content to extract insights, highlight UI issues, or detect elements.

analyze_image

AI-driven analysis of any provided image to derive descriptions, features, or anomalies.

create_stream

Start a live screen streaming session to monitor changes in real time.

get_performance_metrics

Retrieve system health and performance metrics to monitor MCP server load.

Built by

VeilStrat

AI signals for GTM teams