MCP Servers

youtube-mcp

A local MCP server for extracting YouTube video transcripts, metadata, and performing visual analysis using Gemini Vision or local Whisper models. It enables users to process video content through various tools for subtitle retrieval and frame analysis.

README

youtube-mcp

MCP local para extrair transcrições e análise de vídeos do YouTube.

Tools disponíveis

Tool	Método	Dependências
`youtube_transcript`	Legendas via yt-dlp (formato json3)	`python3 -m pip install yt-dlp`
`youtube_info`	Metadata via youtubei.js	Nenhuma extra
`youtube_vision`	Análise visual via Gemini 1.5 Pro	yt-dlp + GEMINI_API_KEY
`youtube_whisper`	Transcrição local via Whisper	yt-dlp + whisper (pip) + FFmpeg

Instalação

cd "MCPs e Skills/youtube-mcp"
npm install

# Instalar yt-dlp (obrigatório para youtube_transcript, youtube_vision, youtube_whisper)
python3 -m pip install yt-dlp

# Instalar Whisper (apenas para youtube_whisper)
python3 -m pip install openai-whisper

# FFmpeg (necessário para Whisper)
winget install ffmpeg

Configuração no Claude Desktop

Adicione em claude_desktop_config.json:

"youtube-mcp": {
  "command": "node",
  "args": ["C:\\Users\\Eric Luciano\\OneDrive\\Documentos\\GitHub\\MCPs e Skills\\youtube-mcp\\index.js"],
  "env": {
    "GEMINI_API_KEY": "sua-chave-aqui"
  }
}

Obtenha sua GEMINI_API_KEY em: https://aistudio.google.com/apikey

Formatos de URL suportados

https://www.youtube.com/watch?v=VIDEO_ID
https://youtu.be/VIDEO_ID
https://www.youtube.com/shorts/VIDEO_ID
ID direto: VIDEO_ID (11 caracteres)

Notas técnicas

youtube_transcript: usa yt-dlp --sub-format json3 que produz legendas limpas sem duplicatas. Fallback automático para inglês se o idioma solicitado não estiver disponível.
youtube_info: usa youtubei.js para obter metadata (título, canal, duração, legendas disponíveis) sem autenticação.
youtube_vision: baixa o vídeo em baixa qualidade, envia para a Google File API e analisa com Gemini 1.5 Pro.
youtube_whisper: baixa apenas o áudio e transcreve localmente com OpenAI Whisper.

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured