Screen Vision MCP Server
The Screen Vision MCP Server gives Claude the ability to see and analyze your screen, camera, and media files — all locally and on-demand.
Screen Capture & Analysis
Capture full screen, region, or window — Take screenshots with optional delay and multi-monitor support
List monitors — Show all connected displays and resolutions
Get active context — Retrieve current window, cursor, and monitor info without capturing an image
Understand screen — AI-powered analysis of what's on screen with optional custom prompts
Text Extraction (OCR)
Read screen text — Extract text from the screen or a specific region
Video & Real-Time Monitoring
Watch screen — Record and sample your screen over time with frame sampling and optional audio transcription
Analyze video — Extract keyframes and metadata from a local video file
Image Analysis
Analyze image — Process local image files (e.g., AirDropped photos or saved screenshots)
Phone Camera Integration
Pair via QR code — Connect your phone as a camera source
Capture camera — Grab the latest frame from a connected phone camera
Watch camera — Stream phone camera with scene detection and optional audio transcription
Phone status — Check the connection status of the phone camera
Security & Privacy
All captures are local and on-demand — nothing runs in the background
Work mode (
SCREEN_VISION_MODE=work) enables PII/PCI scanning, app deny-lists, call detection, rate limiting, and audit logging
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Screen Vision MCP ServerTake a screenshot of my screen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Screen Vision MCP Server
Give Claude Code the ability to see your screen
Screen Vision lets Claude capture screenshots, watch your screen in real-time with audio transcription, analyze video files, and read text via OCR. It runs locally as an MCP server — Claude sees what you see, when you ask.
Privacy & Security
All capture is local and on-demand — no background recording, no persistent process, no external transmission.
Screen Vision runs as a local MCP server (stdio transport). It only captures when Claude explicitly calls a tool in response to your request.
Captured images and transcriptions are sent only to your existing Claude Code session — the same endpoint all Claude Code traffic uses. No third-party services, no cloud storage.
The server does not run in the background between Claude Code sessions. It starts when Claude Code starts and stops when it stops.
No data is written to disk unless you explicitly ask Claude to save a file.
Related MCP server: device-controller-mcp
Quick Start
pip install screen-vision[ocr]Then add to your Claude Code MCP config (.mcp.json):
{
"mcpServers": {
"screen-vision": {
"command": "screen-vision-mcp"
}
}
}System deps for OCR and video:
brew install tesseract # Required for OCR (read_screen_text)
brew install ffmpeg # Required for video analysis (analyze_video)What You Can Say
"Take a screenshot of my screen" → capture_screen
"Capture the Chrome window" → capture_window
"Watch my screen for 1 minute" → watch_screen (with audio transcription)
"Analyze the video at ~/Downloads/demo.mp4" → analyze_video
"Read the text on my screen" → read_screen_text
"What window am I in?" → get_active_context (no screenshot)
"What's on my screen right now?" → understand_screen (AI analysis)
"Analyze this photo I AirDropped" → analyze_imageTools (14)
Tool | What it does | Needs |
| Full screen capture with delay + multi-monitor | — |
| Capture a specific rectangular area | — |
| Capture a window by title | — |
| List displays with resolutions | — |
| Window/cursor/monitor info (no image) | — |
| OCR text extraction from screen | tesseract |
| AI-powered screen analysis | Anthropic API key |
| Analyze a dropped/AirDropped image file | — |
| Watch screen with frame sampling + audio | ffmpeg (audio) |
| Extract keyframes from video files | ffmpeg |
| Grab latest frame from phone camera | — |
| Stream phone camera with scene detection + audio | — |
| Show QR code to connect phone camera | — |
| Check phone camera connection status | — |
Security
Screen Vision includes security controls for corporate environments:
PII/PCI scanning — Detects credit card numbers, SSNs, phone numbers, email addresses in OCR text
App deny-list — Blocks captures of Slack, Teams, Zoom, banking apps, password managers
Call detection — Blocks captures during active audio calls
Rate limits — 200 captures/session, 2s minimum interval, 5min max watch duration
Audit logs — All captures logged to
~/.screen-vision/audit.log
Set SCREEN_VISION_MODE=work to enable all security controls. Default mode is personal (no restrictions).
Dependencies
Core (always installed): mcp[cli], mss, Pillow, numpy, httpx
Extras (mix and match):
Extra | Install | What you get |
|
|
|
|
|
|
|
|
|
|
| All of the above |
Python 3.11+ required.
Development
pip install -e ".[ocr,test]"
pytest tests/ -v
ruff check src/Author
Alex Vicuna — github.com/avicuna
Contributing
Issues and PRs welcome: https://github.com/avicuna/screen-vision
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/avicuna/screen-vision'
If you have feedback or need assistance with the MCP directory API, please join our Discord server