winston-ai-mcp-server

Winston AI MCP Server

Winston AI brings text and image AI detection, plagiarism checks, and text comparison into MCP workflows. It serves academic and professional users checking content originality, likely authorship, and similarity.

Server facts

winston-ai-mcp-server

Project

License
Not specified

Tech

Runtime / language
Not specified
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
9
Last commit
Data as of

Tags

  • Claude
  • Cursor
  • Typescript
  • ai detector
  • claude desktop
  • javascript
  • mcp
  • plagiarism
  • text compare

Overview

Winston AI’s content checks address different questions about authorship and originality through 4 MCP tools. The ai-text-detection tool estimates whether writing is AI-generated, with percentage confidence scores and sentence-level indicators across multiple languages. For visual material, ai-image-detection combines machine-learning analysis with metadata and EXIF inspection, including checks for AI watermarks and their issuers. Supported image formats include WEBP, PNG, JPEG, and JPG. Text detection costs 1 credit per word, while image detection costs 300 credits per image.

For originality checks, plagiarism-detection searches web content for similarities and provides source identification alongside plagiarism analysis. Its uses include academic work, content creation, and legal contexts where originality matters, at 2 credits per word. When the task is to examine a specific pair of texts instead, text-compare reports similarity percentages and word-level matches, with comparison in both directions. That operation costs 0.5 credit per total words across the pair. The server exposes these checks over stdio, covering AI-content assessment, web-source checking, and direct text comparison.

winston-ai-mcp-server setup notes

  • winston-ai-mcp-server records stdio only; confirm a network transport upstream before planning remote access.
  • winston-ai-mcp-server has no recorded license; confirm reuse terms in its repository.

Related MCP servers