Mcp Screenshot
What is Mcp Screenshot
mcp-screenshot is an MCP server designed to capture screenshots and perform OCR (Optical Character Recognition) text recognition from those screenshots.
Use cases
Use cases include automated testing where screenshots are needed for verification, extracting text from user interfaces for documentation purposes, and processing images for data entry tasks.
How to use
To use mcp-screenshot, install it via the command npx -y @kazuph/mcp-screenshot, and configure your claude_desktop_config.json to include the server settings. You can then instruct Claude to take a screenshot and recognize text, specifying the desired area and output format.
Key features
Key features include the ability to capture screenshots of the left half, right half, or full screen, perform OCR text recognition in Japanese and English, and output results in multiple formats such as JSON, Markdown, vertical, and horizontal.
Where to use
mcp-screenshot can be used in various fields including software development, quality assurance, and any application requiring text extraction from images, especially in environments where Japanese text is prevalent.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp Screenshot
mcp-screenshot is an MCP server designed to capture screenshots and perform OCR (Optical Character Recognition) text recognition from those screenshots.
Use cases
Use cases include automated testing where screenshots are needed for verification, extracting text from user interfaces for documentation purposes, and processing images for data entry tasks.
How to use
To use mcp-screenshot, install it via the command npx -y @kazuph/mcp-screenshot, and configure your claude_desktop_config.json to include the server settings. You can then instruct Claude to take a screenshot and recognize text, specifying the desired area and output format.
Key features
Key features include the ability to capture screenshots of the left half, right half, or full screen, perform OCR text recognition in Japanese and English, and output results in multiple formats such as JSON, Markdown, vertical, and horizontal.
Where to use
mcp-screenshot can be used in various fields including software development, quality assurance, and any application requiring text extraction from images, especially in environments where Japanese text is prevalent.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
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:
-
- 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
npx -y @kazuph/mcp-screenshot
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 | 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
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
