mcp screenshot

Local 2025-08-31 23:25:05 0
Os Automation @kazuph/mcp-screenshot

Provides screenshot and OCR capabilities for macOS.

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

mcp-screenshot MCP server

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
  2. Primary OCR engine
  3. High-accuracy Japanese text recognition

  4. Runs as an API server

  5. Tesseract.js

  6. Fallback OCR engine
  7. Used when yomitoku is unavailable
  8. Supports both Japanese and English recognition

Installation

npx -y @kazuph/mcp-screenshot

Claude Desktop Configuration

Add the following configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "screenshot": {
      "command": "npx",
      "args": ["-y", "@kazuph/mcp-screenshot"],
      "env": {
        "OCR_API_URL": "http://localhost:8000"  // yomitoku API base URL
      }
    }
  }
}

Environment Variables

Variable Name Description Default Value
OCR_API_URL yomitoku API base URL http://localhost:8000

Usage Example

You can use it by instructing Claude like this:

Please take a screenshot of the left half of the screen and recognize the text in it.

Tool Specification

capture

Takes a screenshot and performs OCR.

Options: - region: Screenshot area ('left'/'right'/'full', default: 'left') - format: Output format ('json'/'markdown'/'vertical'/'horizontal', default: 'markdown')

License

MIT

Author

kazuph

[
  {
    "description": "Captures a screenshot of the specified region and performs OCR. Options:n- region: 'left'/'right'/'full' (default: 'left')n- format: 'json'/'markdown'/'vertical'/'horizontal' (default: 'markdown')nThe screenshot is saved to a dated directory in Downloads.",
    "inputSchema": {
      "$schema": "http://json-schema.org/draft-07/schema#",
      "additionalProperties": false,
      "properties": {
        "format": {
          "default": "markdown",
          "enum": [
            "json",
            "markdown",
            "vertical",
            "horizontal"
          ],
          "type": "string"
        },
        "region": {
          "default": "left",
          "enum": [
            "left",
            "right",
            "full"
          ],
          "type": "string"
        }
      },
      "type": "object"
    },
    "name": "capture"
  }
]