markdownify-mcp MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

10 converters: PDF, DOCX, XLSX, PPTX, images, audio, YouTube, Bing search, web pages
Uniform tool shape: give a path or URL, get markdown
Audio transcription via OpenAI Whisper-compatible backend
Works with local files and remote URLs
Node-based; stdio transport

Live-Demo

In der Praxis

markdownify.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

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

{
  "mcpServers": {
    "markdownify": {
      "command": "npx",
      "args": [
        "-y",
        "markdownify-mcp"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "markdownify": {
      "command": "npx",
      "args": [
        "-y",
        "markdownify-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "markdownify": {
      "command": "npx",
      "args": [
        "-y",
        "markdownify-mcp"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "markdownify": {
      "command": "npx",
      "args": [
        "-y",
        "markdownify-mcp"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "markdownify",
      "command": "npx",
      "args": [
        "-y",
        "markdownify-mcp"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "markdownify": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "markdownify-mcp"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add markdownify -- npx -y markdownify-mcp

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: markdownify-mcp

How to ingest a folder of PDFs into a markdown knowledge base

👤 RAG builders, knowledge managers ⏱ ~30 min intermediate

Wann einsetzen: You have 50 PDF research papers and want clean text to embed.

Voraussetzungen

pnpm — npm i -g pnpm
Install + run — git clone the repo, pnpm install, pnpm start

Ablauf

Enumerate files

List every .pdf under /library/papers/.✓ Kopiert

→ Path list
Convert in batch

For each, call pdf-to-markdown. Write the output to /library/markdown/<same-name>.md.✓ Kopiert

→ Markdown files appear
Spot-check one

Show me the first 500 chars of /library/markdown/attention-is-all-you-need.md.✓ Kopiert

→ Legible markdown, no PDF artifacts

Ergebnis: A parallel /markdown/ tree ready to embed.

Fallstricke

Scanned PDFs (image-only) produce empty markdown — Pre-OCR scanned PDFs before conversion
Math-heavy PDFs lose equations — For math, try pairing with Mathpix or the nougat OCR model separately

Kombinieren mit: filesystem

How to turn a meeting recording into searchable notes

👤 Anyone recording meetings ⏱ ~10 min beginner

Wann einsetzen: Post-call, before memory fades.

Voraussetzungen

OpenAI key for Whisper — platform.openai.com (or any Whisper-compatible endpoint)

Ablauf

Transcribe

audio-to-markdown on /recordings/2026-04-14-standup.m4a.✓ Kopiert

→ Markdown with timestamps
Extract actions

From the transcript, list action items with owners.✓ Kopiert

→ Action checklist

Ergebnis: Searchable meeting notes + actions.

Fallstricke

Whisper mislabels speakers — For speaker diarization, use a specialized tool; markdownify gives you text only

Kombinieren mit: notion

How to summarize a YouTube video without watching it

👤 Researchers, learners ⏱ ~5 min beginner

Wann einsetzen: A 90-minute video in your feed when you have 5 minutes.

Ablauf

Pull transcript

youtube-to-markdown https://youtu.be/xyz123.✓ Kopiert

→ Transcript markdown
Summarize

Summarize in 5 bullets + key timestamps.✓ Kopiert

→ Bulleted summary with jump points

Ergebnis: Decision on whether to actually watch the video.

Fallstricke

Some videos have captions disabled — The tool returns empty — fall back to audio-to-markdown if you have the file

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

markdownify + filesystem

Batch-convert an inbox folder to a knowledge base folder

Convert every file in /inbox/ to markdown under /kb/ preserving the directory tree.✓ Kopiert

markdownify + notion

Drop converted docs straight into Notion

Convert the PDF /specs/rfq-2026.pdf and create a Notion page with the result.✓ Kopiert

markdownify + excel

Combine xlsx-to-markdown with excel MCP for round-tripping

Read /report.xlsx sheet 'Summary', convert to markdown, and save to /docs/report.md.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
pdf-to-markdown	path_or_url: str	Convert PDFs	free (local)
docx-to-markdown	path_or_url: str	Word docs	free
xlsx-to-markdown	path_or_url: str	Spreadsheets as tables	free
pptx-to-markdown	path_or_url: str	Slide decks	free
image-to-markdown	path_or_url: str	Images	free or 1 LLM call if OCR enabled
audio-to-markdown	path: str	Audio/voice memos	1 Whisper call ($0.006/min)
youtube-to-markdown	url: str	YouTube captions	free
webpage-to-markdown	url: str	Readable web text	free
bing-search-to-markdown	query: str	Quick web search	free
get-markdown-file	path: str	Retrieve a prior conversion	free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None for local converters; Whisper/OpenAI for audio
Tokens pro Aufruf: Depends on doc size
Kosten in €: Free except audio transcription (~$0.006/min via Whisper)
Tipp: For large PDF batches, do conversion before pasting into the LLM — cheaper than asking Claude to parse PDFs directly.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: Filesystem read on source files, write on output

Credential-Speicherung: OPENAI_API_KEY (for audio) in env

Datenabfluss: Local converters stay local. Audio goes to your Whisper endpoint.

Niemals gewähren: Don't run untrusted URLs through webpage-to-markdown without sandboxing — SSRF risk

pptx/docx converters occasionally lose formatting; review before using as source of truth.

Fehlerbehebung

Häufige Fehler und Lösungen

pnpm install fails

Node version too old — requires Node 18+. nvm install 20.

Prüfen: node -v

pdf-to-markdown returns empty string

Likely a scanned PDF (image-only). Run OCR first (ocrmypdf).

youtube-to-markdown 'no captions available'

Video owner disabled captions. Download audio and use audio-to-markdown instead.

audio-to-markdown 401

Missing or invalid OPENAI_API_KEY.

Prüfen: echo $OPENAI_API_KEY

Alternativen

markdownify-mcp vs. andere

Alternative	Wann stattdessen	Kompromiss
markitdown (Microsoft)	You want the underlying converter directly without MCP	No MCP interface; needs your own wrapping
unstructured.io	Enterprise-scale ingestion with layout awareness	Paid for advanced features

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen