mcp-screenshot

mcp-screenshot

12
os_automation

MCP Screenshot is a server that allows for screenshot capturing and OCR text recognition, supporting Japanese and English. It features multiple output formats and uses both yomitoku and Tesseract.js as OCR engines.

MCP Screenshot

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

Features

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

OCR Engines

This server uses two OCR engines:

  1. yomitoku (high-accuracy Japanese text recognition, runs as an API server)
  2. Tesseract.js (fallback engine, supports Japanese and English)

Usage Example

Instruct Claude for screenshots and text recognition, for example, "Please take a screenshot of the left half of the screen and recognize the text in it."

Tool Specification

capture

  • Options: region (left/right/full, default: left), format (json/markdown/vertical/horizontal, default: markdown)