mcp-screenshot

mcp-screenshot

3.4

If you are the rightful owner of mcp-screenshot 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.

An MCP server that captures screenshots and performs OCR text recognition.

The MCP Screenshot server is designed to capture screenshots and perform Optical Character Recognition (OCR) on the captured images. It supports capturing screenshots of the left half, right half, or the full screen and can recognize text in both Japanese and English. The server provides multiple output formats including JSON, Markdown, vertical, and horizontal text arrangements. It utilizes two OCR engines: 'yomitoku' for high-accuracy Japanese text recognition and 'Tesseract.js' as a fallback option. The server is easy to install and configure, making it a versatile tool for users needing automated screenshot and text recognition capabilities.

Features

  • Screenshot capture (left half, right half, full screen)
  • OCR text recognition (supports Japanese and English)
  • Multiple output formats (JSON, Markdown, vertical, horizontal)

Tools

  1. capture

    Capture screenshots and perform OCR recognition