What is Mcp Desktop Dvr

mcp-desktop-dvr is a Model Context Protocol (MCP) server designed for desktop video capture and analysis on macOS. It enables intelligent video capture with a 30-minute rolling buffer for analyzing desktop activities.

Use cases

Use cases for mcp-desktop-dvr include recording coding sessions for later review, analyzing user interactions during usability tests, monitoring employee productivity in remote work settings, and creating instructional videos based on desktop activities.

How to use

To use mcp-desktop-dvr, clone the repository from GitHub, install the dependencies using npm, and build the project. You can run the MCP server in development mode or production mode using the respective npm commands.

Key features

Key features include continuous desktop recording with hardware-accelerated encoding, a 30-minute rolling buffer for capturing recent activities, on-demand analysis of video segments, low resource usage, and native support for macOS.

Where to use

mcp-desktop-dvr can be used in various fields such as software development, user experience research, remote work monitoring, and educational environments where screen activity analysis is beneficial.

MCP Desktop DVR

✅ PRODUCTION READY

MCP server for desktop video capture and analysis on macOS. Enables Claude to analyze screen activity through a 30-minute rolling buffer.

Features

• 30-minute rolling buffer of desktop activity
• AI-powered visual analysis with OpenAI GPT-4o (cloud) or Tarsier2-7B (local)
• Intelligent fallback from OpenAI → Tarsier → OCR
• Window-specific capture by application
• Precise extraction of time segments
• Production-ready with comprehensive testing

Requirements

• macOS 10.15+
• Node.js 18+
• Screen Recording permission

Quick Setup

npm install && npm run build

Add to Claude Desktop config:

Tools

• start-continuous-capture - Begin recording
• analyze-desktop-now - Extract and analyze recent activity
• get-capture-status - Check recording status
• stop-capture - Stop recording
• configure-capture - Update settings

Usage

Ask Claude:

• “Start desktop recording”
• “Analyze the last 30 seconds”
• “What errors are on my screen?”

Video Analysis Options

The analyze-desktop-now tool supports multiple analyzers with different strengths:

☁️ OpenAI GPT-4o Vision (Primary - Cloud)

• Most accurate analysis using GPT-4o via Responses API
• Automatic GIF segmentation - creates 10-second segments from videos
• Smart file management - preserves all GIF files locally alongside MP4
• Efficient uploads - sends only first segment to OpenAI for analysis
• Comprehensive understanding of complex workflows
• Requires OpenAI API key and internet connection
• Fast processing (~3-5 seconds)

🤖 Tarsier2-7B (Fallback - Local AI)

• Runs locally on your Mac using Metal Performance Shaders
• No API keys required - completely private
• Excellent visual understanding of UIs, games, and graphics
• Moderate processing time (~5-15 seconds for 30-second clips)

📝 OCR Text Extraction (Final Fallback)

• Basic text extraction from screenshots
• Limited effectiveness with modern UIs
• Always available as final fallback

Configuration

Set environment variables in your MCP config:

Analyzer Selection Logic

• "auto" (default) - Uses OpenAI if API key set, otherwise Tarsier, then OCR
• "openai" - Forces OpenAI GPT-4o Vision (requires API key)
• "tarsier" - Forces Tarsier2-7B local AI
• "ocr" - Forces basic OCR text extraction

Documentation

• User Guide - Setup and usage instructions
• CLAUDE.md - Development info

License

ISC