Minimax MCP Tools

What is Minimax MCP Tools?

Minimax MCP Tools is a Model Context Protocol (MCP) server for Minimax AI integration, providing asynchronous image generation and text-to-speech with advanced rate limiting and error handling, designed for batch content creation.

How to use Minimax MCP Tools?

Add the server to your MCP settings with command: "npx", args: ["minimax-mcp-tools"], and set the MINIMAX_API_KEY environment variable. Use the included tools (submit_image_generation, submit_speech_generation, task_barrier) via the MCP client to submit tasks and wait for results.

Key features of Minimax MCP Tools

• Async submit-and-barrier pattern for batch content creation
• Adaptive rate limiting (10 RPM images, 20 RPM speech) with burst capacity
• Barrier synchronization retrieves all task results at once
• Supports image generation with optional parameters (aspect ratio, custom size, seed, references, style)
• Supports text-to-speech with voice, speed, pitch, emotion, and sound effect options
• Tasks execute in background and return immediately with task IDs

Use cases of Minimax MCP Tools

• Narrated slideshow production – generate slide images and narration in parallel
• AI-driven audiobook creation – produce chapters with multiple voice characters simultaneously
• Website asset generation – create consistent visual and audio elements for web projects
• Multimedia content pipelines – LLM-driven workflows requiring both visuals and audio

FAQ from Minimax MCP Tools

What are the rate limits for image and speech generation?

Image generation is limited to 10 requests per minute, and speech generation to 20 requests per minute, with burst capacity allowed.

How does the async submit-and-barrier pattern work?

You submit tasks (image or speech) one by one; they return immediately with task IDs and execute in the background. Calling task_barrier waits for all submitted tasks to complete and returns a comprehensive results summary.

What parameters are required for image generation?

prompt and outputFile are required. Optional parameters include aspectRatio, customSize, seed, subjectReference, and style.

What parameters are required for speech generation?

text and outputFile are required. Optional parameters include highQuality, voiceId, speed, volume, pitch, emotion, format, sampleRate, bitrate, languageBoost, intensity, timbre, and sound_effects.

What runtime or dependencies are needed?

The server is run via npx minimax-mcp-tools and requires a Minimax API key set as the MINIMAX_API_KEY environment variable. No local installation or additional dependencies are listed beyond Node.js (implied by npx).