youtube-fetcher-to-markdown MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Any YouTube URL format accepted (short, embed, playlist, watch)
YAML frontmatter for Obsidian Dataview querying across transcripts
Optional timestamps, language choice, JSON/SRT output
Chapter-aware markdown when the video has chapters
File naming with date + slug + video ID for stable sorting

Démo en direct

Aperçu en pratique

youtube-fetcher-to-markdown-skill.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "youtube-fetcher-to-markdown-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
        "~/.claude/skills/youtube-fetcher-to-markdown"
      ],
      "_inferred": true
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "youtube-fetcher-to-markdown-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
        "~/.claude/skills/youtube-fetcher-to-markdown"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "youtube-fetcher-to-markdown-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
        "~/.claude/skills/youtube-fetcher-to-markdown"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "youtube-fetcher-to-markdown-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
        "~/.claude/skills/youtube-fetcher-to-markdown"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "youtube-fetcher-to-markdown-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
        "~/.claude/skills/youtube-fetcher-to-markdown"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

{
  "context_servers": {
    "youtube-fetcher-to-markdown-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/JimmySadek/youtube-fetcher-to-markdown",
          "~/.claude/skills/youtube-fetcher-to-markdown"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add youtube-fetcher-to-markdown-skill -- git clone https://github.com/JimmySadek/youtube-fetcher-to-markdown ~/.claude/skills/youtube-fetcher-to-markdown

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : youtube-fetcher-to-markdown

Archive a YouTube lecture series as a searchable Obsidian vault

👤 Self-learners and researchers ⏱ ~20 min beginner

Quand l'utiliser : You're studying from YouTube and want to search across 20+ videos later.

Prérequis

Skill cloned — git clone https://github.com/JimmySadek/youtube-fetcher-to-markdown ~/.claude/skills/youtube-fetcher-to-markdown
yt-dlp or equivalent installed — brew install yt-dlp

Déroulement

Fetch a playlist's transcripts

youtube-fetcher-to-markdown — fetch every video in playlist <URL>, include timestamps, source=cs-course.✓ Copié

→ ~/yt_transcripts/ fills with per-video markdown files, all tagged source: cs-course
Query via Dataview

In Obsidian, write a Dataview query listing all cs-course videos sorted by upload date.✓ Copié

→ Dataview returns the set because the frontmatter is consistent

Résultat : A queryable knowledge base you can grep, tag, and cross-link.

Pièges

Some videos have no captions and the transcript is empty — Check the skill's log; fall back to Whisper locally for those

Combiner avec : filesystem

Turn a YouTube talk into a blog post draft

👤 Creators repurposing content ⏱ ~25 min beginner

Quand l'utiliser : Your talk went up; you want a written version for SEO.

Déroulement

Fetch the transcript

youtube-fetcher-to-markdown <URL> with chapters and timestamps.✓ Copié

→ Markdown with chapter-delimited sections
Rewrite as blog

Now draft a blog post from this transcript.✓ Copié

→ Structured post using the chapters as section anchors

Résultat : Draft-quality blog post based on your own talk.

Combiner avec : seo-blog-writer-claude-skill

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

youtube-fetcher-to-markdown-skill + filesystem

Route transcripts into a specific Obsidian vault folder with custom naming

Save fetched transcripts to ~/obsidian/sources/youtube/.✓ Copié

youtube-fetcher-to-markdown-skill + seo-blog-writer-claude-skill

Fetch transcript → generate blog post in one chain

Fetch the transcript for <URL>, then seo-blog-writer target keyword 'X'.✓ Copié

youtube-fetcher-to-markdown-skill + claude-content-writer-skill

Turn transcripts into newsletters in your brand voice

Fetch transcript, then claude-content-writer newsletter version in my voice profile.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
fetch_single	URL + options (timestamps, lang, format, source)	One video at a time
fetch_playlist	playlist URL + options	Bulk archiving
export_json	URL	You want the data in a non-markdown pipeline

Coût et limites

Coût d'exécution

Quota d'API: YouTube has no explicit scrape quota for captions but be reasonable
Tokens par appel: Proportional to video length
Monétaire: Free — skills are local files
Astuce: For very long videos, use JSON export + snippet extraction instead of loading full transcripts into context.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : No credentials — pure prompts

Sortie de données : Fetches from YouTube. No data leaves your machine afterward.

Respect YouTube's ToS and creators' rights when redistributing transcripts.
Don't rely on auto-captions as ground truth for quotes — they have errors.

Dépannage

Erreurs courantes et correctifs

Skill not invoked — Claude summarizes without fetching

Say 'fetch the transcript using youtube-fetcher-to-markdown' explicitly.

Vérifier : ls ~/.claude/skills/youtube-fetcher-to-markdown/SKILL.md

SKILL.md frontmatter wrong

Re-clone; description drives activation.

Vérifier : head ~/.claude/skills/youtube-fetcher-to-markdown/SKILL.md

Wrong trigger keywords — transcript has no timestamps

Pass --timestamps explicitly in the prompt.

Alternatives

youtube-fetcher-to-markdown vs autres

Alternative	Quand l'utiliser	Compromis
Whisper (local)	No captions available on the video	Needs GPU or patience; better accuracy on accented speech
Online transcript sites	One-off copy-paste	No Obsidian integration, no structured frontmatter

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills