MiniMax-MCP MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

text_to_audio with multiple voices
voice_clone from audio samples
voice_design — generate a voice from a text description
text_to_image and generate_video (async with query_video_generation)
music_generation with lyrics input

Live-Demo

In der Praxis

minimax.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": {
    "minimax": {
      "command": "uvx",
      "args": [
        "MiniMax-MCP"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": [
        "MiniMax-MCP"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": [
        "MiniMax-MCP"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "minimax": {
      "command": "uvx",
      "args": [
        "MiniMax-MCP"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "minimax",
      "command": "uvx",
      "args": [
        "MiniMax-MCP"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "minimax": {
      "command": {
        "path": "uvx",
        "args": [
          "MiniMax-MCP"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add minimax -- uvx MiniMax-MCP

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

Anwendungsfälle

Praxisnahe Nutzung: MiniMax-MCP

How to turn a blog post into narration audio

👤 Creators, podcasters, accessibility teams ⏱ ~15 min beginner

Wann einsetzen: You want a listenable version of written content.

Voraussetzungen

MiniMax account + API key — Global: minimax.io; Mainland: minimaxi.com. Set MINIMAX_API_KEY + MINIMAX_API_HOST matching region
uvx installed — brew install uv

Ablauf

List voices

list_voices — show all available voices in English.✓ Kopiert

→ Voice catalog with previews
Render audio

text_to_audio: [paste article] with voice 'female-calm-en'. Save to /audio/article.mp3.✓ Kopiert

→ MP3 file saved, URL returned

Ergebnis: Listenable audio version of your content.

Fallstricke

Long articles hit per-call character limits — Split into paragraphs, render, and concatenate
Pronunciation of proper nouns is off — Use SSML-style phonetic hints or the voice_design tool for specialized voices

Kombinieren mit: filesystem

How to clone your own voice for narration

👤 Creators wanting a consistent narrator ⏱ ~10 min intermediate

Wann einsetzen: You want AI narration in your own voice.

Voraussetzungen

10-60 second voice sample (clean audio, your voice) — Record via your phone; export as mp3/wav

Ablauf

Clone

voice_clone with sample /recordings/me.wav, name 'my-voice'.✓ Kopiert

→ Voice id returned
Use it

text_to_audio with voice='my-voice' on [paste text].✓ Kopiert

→ Output in your voice

Ergebnis: Personal narration without a mic every time.

Fallstricke

Using someone else's voice without consent — Don't — legal and ethical issue; use voice_design instead

How to generate an image and turn it into a short video

👤 Content creators, marketers ⏱ ~15 min intermediate

Wann einsetzen: Social content, product previews.

Ablauf

Generate image

text_to_image: 'minimal studio product shot of a ceramic mug, natural light'.✓ Kopiert

→ Image URL
Animate

generate_video with prompt 'slow rotating mug on a wooden table'. Poll status with query_video_generation.✓ Kopiert

→ Video URL when ready

Ergebnis: Short marketing clip.

Fallstricke

Video generation is async and can take minutes — Always use query_video_generation to poll — don't block a chat waiting

Kombinieren mit: google-workspace

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

minimax + filesystem

Save generated assets into a structured content folder

Generate narration for each chapter in /manuscript/ and save MP3s to /audio/chapters/.✓ Kopiert

minimax + google-workspace

Produce audio from a Google Doc, then attach as a link in the doc

Read Doc 'Launch Post', generate narration, upload to Drive, append the link as a footer.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
text_to_audio	text: str, voice: str, format?: 'mp3'\|'wav', output_path?	Narrate text	Per MiniMax TTS pricing
list_voices	language?: str	Find a voice	free
voice_clone	sample_path: str, name: str	Custom voice	Per MiniMax pricing
voice_design	description: str	Generate a voice from prose	Per MiniMax pricing
text_to_image	prompt: str, aspect_ratio?	Image gen	Per MiniMax image pricing
generate_video	prompt: str, duration_s?	Kick off video gen	Per MiniMax video pricing
query_video_generation	task_id	Poll video job	free
music_generation	lyrics: str, genre?: str	Create a short track	Per MiniMax music pricing

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Per MiniMax plan — check current pricing at minimax.io or minimaxi.com
Tokens pro Aufruf: Modest text input; outputs are audio/image/video files
Kosten in €: Pay-per-call; cheapest to start with Flash/Hailuo-Mini equivalents
Tipp: Batch short TTS into fewer longer calls when possible; video is the most expensive — cache results.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: MINIMAX_API_KEY + MINIMAX_API_HOST matched to region

Credential-Speicherung: Env vars

Datenabfluss: Your text/audio goes to MiniMax's servers in the selected region

Niemals gewähren: Don't mix global and mainland keys — causes 'Invalid API key'

Cloned voices are powerful; only clone voices you have explicit consent to use.
Generated content may be subject to platform TOS — review before commercial use.

Fehlerbehebung

Häufige Fehler und Lösungen

Invalid API key

Key and host region must match. Set MINIMAX_API_HOST=https://api.minimax.io for global or https://api.minimaxi.com for mainland.

Prüfen: env | grep MINIMAX

video generation never completes

Poll with query_video_generation up to 10 min; longer-than-expected usually means server load. Retry with a new task if stuck.

voice_clone quality poor

Sample audio must be 10-60s, clean (no music/noise), single speaker.

Rate limit exceeded

MiniMax enforces per-minute and per-day caps. Back off; upgrade plan for higher limits.

Alternativen

MiniMax-MCP vs. andere

Alternative	Wann stattdessen	Kompromiss
ElevenLabs MCP	You want Western-market-focused TTS with dedicated English voices	No video/image/music in one bundle
OpenAI/Whisper for TTS	You already have OpenAI credits	Fewer voice options than MiniMax

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen