Skip to content

guimatheus92/mcp-video-analyzer

v0.2.4 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 2mo MCP Data & Storage
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai claude frames loom mcp mcp-server
+4 more
model-context-protocol ocr transcript video-analysis

Summary

AI summary

Fixed OCR dropping accented characters by changing default language to English + Portuguese and adding a customizable ocrLanguage parameter.

Full changelog

What's New

Multilingual OCR Support

  • Fixed: OCR was dropping accented characters (é, ã, ç, ô → ?) because Tesseract was hardcoded to English only
  • Default language: Now eng+por (English + Portuguese) — accented characters are correctly recognized
  • New parameter: ocrLanguage on analyze_video and analyze_moment tools — customize for any language (e.g., "eng+spa", "eng+fra+deu")

Install

npx [email protected]

Full Changelog: https://github.com/guimatheus92/mcp-video-analyzer/compare/v0.2.3...v0.2.4

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track guimatheus92/mcp-video-analyzer

Get notified when new releases ship.

Sign up free

About guimatheus92/mcp-video-analyzer

MCP server for video analysis — extracts transcripts, key frames, OCR text, and annotated timelines from video URLs. Supports Loom and direct video files (.mp4, .webm). Zero auth required.

All releases →

Related context

Beta — feedback welcome: [email protected]