Supports outputting OCR results in Markdown format
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-screenshotcapture the right half of my screen and extract the text as JSON"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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)
Related MCP server: Screenshot MCP Server
OCR Engines
This server uses two OCR engines:
Primary OCR engine
High-accuracy Japanese text recognition
Runs as an API server
Fallback OCR engine
Used when yomitoku is unavailable
Supports both Japanese and English recognition
Installation
Claude Desktop Configuration
Add the following configuration to your claude_desktop_config.json:
Environment Variables
Variable Name | Description | Default Value |
OCR_API_URL | yomitoku API base URL |
Usage Example
You can use it by instructing Claude like this:
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
Appeared in Searches
- MCP server for screenshot viewing and automatic cropping
- How to connect to the internet, browse a webpage, and take screenshots
- A microcontroller with image processing capabilities
- A system or tool for enabling computer vision capabilities in an MCP (Microcontroller Platform)
- Tools and Methods for Image Generation