trackmcp
Back to directory
kazuph

mcp-screenshot

View on GitHub

Repository for MCP screenshot functionality

21 stars JavaScriptOthers Updated Oct 3, 2025

Documentation

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

    2. Tesseract.js

      Installation

      bash
      npx -y @kazuph/mcp-screenshot

      Claude Desktop Configuration

      Add the following configuration to your `claude_desktop_config.json`:

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

      Environment Variables

      Variable NameDescriptionDefault Value
      OCR_API_URLyomitoku API base URLhttp://localhost:8000

      Usage Example

      You can use it by instructing Claude like this:

      code
      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

      Frequently asked questions

      What is mcp-screenshot?

      mcp-screenshot is Repository for MCP screenshot functionality

      How do I install mcp-screenshot?

      Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

      Is mcp-screenshot open source?

      Yes — it is hosted on GitHub at https://github.com/kazuph/mcp-screenshot and has 21 stars.

      Related MCP tools

      mikechambersadb-mcp

      Adb-mcp is a proof of concept project to enabled AI control of Adobe tools (Adobe Photoshop and Adobe Premiere) by providing an interface to LLMs via the MCP...

      391 JavaScript
      Mintplex-Labsanything-llm

      The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

      50,686 JavaScript
      ai-agentscustom-ai-agentsdeepseek+16
      eyaltoledanoclaude-task-master

      An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others. Built for the Model Context Protocol to enhance AI capabiliti

      23,033 JavaScript
      aicursorcursor-ai+9
      xszyoufay

      Fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的mcp框架。 JavaScript-based implementation. Trusted by 12000+ developers.

      12,003 JavaScript
      aiandroidapi+4
      sonnylazuardicursor-talk-to-figma-mcp

      CTTF: MCP integration between Cursor and Figma, allowing Cursor Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

      5,539 JavaScript
      agentagenticagentic-ai+11
      mendableaifirecrawl-mcp-server

      🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients. JavaScript-based implementation.

      4,847 JavaScript
      batch-processingclaudecontent-extraction+11

      Run your own MCP server? See who uses it and what to fix.

      Measure it with TrackMCP