MCP Screenshot and OCR

MCPOpen SourceMIT41.7

by kazuph • Tools & CLI

An MCP server for capturing screenshots and performing OCR text recognition, supporting multiple languages and formats.

Example Use Cases

1
Capture and analyze text from screen regions efficiently.
2
Reliable OCR support for both Japanese and English languages.
3
Versatile output formats for processed OCR text.

Description

The MCP Screenshot server enables users to capture screenshots and extract text using OCR technology. It supports Japanese and English text recognition and provides various output formats such as JSON and Markdown. The server utilizes the high-accuracy yomitoku OCR engine and Tesseract.js as a fallback, ensuring reliable text extraction for various use cases.

Capabilities(1 total)

Tools (1)

capture

Captures a screenshot of the specified region and performs OCR. Options: - region: 'left'/'right'/'full' (default: 'left') - format: 'json'/'markdown'/'vertical'/'horizontal' (default: 'markdown') The screenshot is saved to a dated directory in Downloads.

region:stringformat:string

Quick Actions

View on GitHub

Security

Scanned 2 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C58/100

7/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelUnknown

Capabilities1 Tools / 0 Prompts / 0 Resources

Ownerkazuph

CategoryTools & CLI

DependenciesStandalone

Set Your Username