TIMBOTGPT/screen-vision-mcp
If you are the rightful owner of screen-vision-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Screen Vision MCP Server is a Model Context Protocol server designed for macOS, offering advanced screen capture, OCR, and visual understanding capabilities.
Tools
Functions exposed to the LLM to take actions
capture_fullscreen
Capture the entire screen.
capture_window
Capture a specific application window.
capture_region
Capture a specific region of the screen.
extract_text_from_screen
Capture screen and extract text using OCR.
find_text_on_screen
Find text on screen and return its location.
get_window_list
Get list of all open windows with their positions.
get_screen_info
Get information about available screens/displays.
click_at_position
Click at a specific screen position.
monitor_screen_region
Monitor a screen region for changes over time.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client