MiniMax MCP Server
Enables Model Context Protocol (MCP) clients to access advanced text-to-speech, voice cloning, image and video generation APIs with regional API key support and flexible transport options.
Supercharge Your AI with MiniMax MCP Server
Unlock the full potential of MiniMax MCP Server through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
Local output directory path for saved resources
Your MiniMax API key from the MiniMax platform
MiniMax API host endpoint - varies by region (Global: https://api.minimaxi.chat, Mainland: https://api.minimax.chat)
https://api.minimaxi.chatHow resources are provided - 'url' (default) or 'local'
urlSecurity Notice
Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.
JavaScript/TypeScript implementation of a Model Context Protocol server offering image and video generation, text-to-speech, voice cloning, and dynamic configuration for seamless integration with MCP-compatible clients and platforms.
Added May 30, 2025
Enables seamless interaction with advanced Text-to-Speech and audio processing APIs via Model Context Protocol, offering voice cloning, speech generation, transcription, and customizable audio features for MCP clients.
Added May 30, 2025
Enables MCP clients to access avatar and video generation, voice retrieval, and account credit management via the HeyGen API, supporting seamless integration with Model Context Protocol tools.
Added May 30, 2025
Implements the Model Context Protocol to support SDK development with advanced prompt templates, code and game resource search, and comprehensive game asset generation tools including images, audio, cinematics, and skyboxes via multiple transport options.
8 toolsAdded May 30, 2025
Model Context Protocol server integrating Minimax API for AI-driven high-quality image generation from text prompts and customizable natural-sounding text-to-speech conversion with multiple voice, emotion, and audio format options.
2 toolsAdded May 30, 2025