The Minimax MCP Tools server integrates Minimax AI capabilities into your Model Context Protocol (MCP) setup, providing asynchronous image generation and text-to-speech functionality with intelligent rate limiting. It's designed for batch content creation workflows where you need to generate multiple media assets efficiently.
To use the Minimax MCP Tools server, you need to add it to your MCP configuration:
{
"mcpServers": {
"minimax-mcp-tools": {
"command": "npx",
"args": ["minimax-mcp-tools"],
"env": {
"MINIMAX_API_KEY": "your_api_key_here"
}
}
}
}
Make sure to replace your_api_key_here with your actual Minimax API key.
You can submit image generation tasks asynchronously with the submit_image_generation tool:
// Example usage
const result = await mcp.invoke("minimax-mcp-tools.submit_image_generation", {
prompt: "A serene mountain landscape at sunset",
outputFile: "./images/landscape.png",
// Optional parameters
aspectRatio: "16:9",
// customSize: {width: 1024, height: 576},
// seed: 42,
// subjectReference: "URL_TO_REFERENCE_IMAGE",
// style: "realistic"
});
Required:
prompt: Text description of the image to generateoutputFile: Path where the generated image will be savedOptional:
aspectRatio: Aspect ratio of the generated image (e.g., "16:9", "4:3")customSize: Custom dimensions object with width and heightseed: Seed value for reproducible resultssubjectReference: Reference image URLstyle: Style guidance for the imageYou can convert text to speech asynchronously with the submit_speech_generation tool:
// Example usage
const result = await mcp.invoke("minimax-mcp-tools.submit_speech_generation", {
text: "Hello world, this is a text-to-speech demonstration.",
outputFile: "./audio/demo.mp3",
// Optional parameters
highQuality: true,
voiceId: "male-01",
speed: 1.0,
// Additional optional parameters available
});
Required:
text: The text to convert to speechoutputFile: Path where the audio file will be savedOptional:
highQuality: Boolean to enable high-quality modevoiceId: ID of the voice to usespeed: Playback speed multipliervolume: Audio volume levelpitch: Voice pitch adjustmentemotion: Emotional tone of the speechformat: Audio format (default is MP3)sampleRate: Audio sample ratebitrate: Audio bitratelanguageBoost: Language enhancement settingsintensity: Voice intensity leveltimbre: Voice timbre adjustmentssound_effects: Additional sound effects to applyAfter submitting multiple tasks, you can wait for all of them to complete using the task_barrier tool:
// Example usage after submitting multiple tasks
const barrierResult = await mcp.invoke("minimax-mcp-tools.task_barrier", {});
// Now all your images and audio files are ready at the paths you specified
The server is designed for efficient batch content creation. Here's an example workflow:
// Submit multiple tasks in quick succession
const imageTask1 = await mcp.invoke("minimax-mcp-tools.submit_image_generation", {
prompt: "A futuristic city skyline",
outputFile: "./images/city.png"
});
const speechTask1 = await mcp.invoke("minimax-mcp-tools.submit_speech_generation", {
text: "Welcome to the future city tour.",
outputFile: "./audio/intro.mp3"
});
const imageTask2 = await mcp.invoke("minimax-mcp-tools.submit_image_generation", {
prompt: "A high-tech transportation system",
outputFile: "./images/transport.png"
});
// Wait for all tasks to complete
const results = await mcp.invoke("minimax-mcp-tools.task_barrier", {});
// Now all files are available for use
console.log("All media assets generated successfully");
This pattern allows you to maximize throughput while respecting API rate limits (10 RPM for images, 20 RPM for speech).
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "minimax-mcp-tools" '{"command":"npx","args":["minimax-mcp-tools"],"env":{"MINIMAX_API_KEY":"your-minimax-api-key","MINIMAX_GROUP_ID":"your-minimax-group-id"}}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"minimax-mcp-tools": {
"command": "npx",
"args": [
"minimax-mcp-tools"
],
"env": {
"MINIMAX_API_KEY": "your-minimax-api-key",
"MINIMAX_GROUP_ID": "your-minimax-group-id"
}
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"minimax-mcp-tools": {
"command": "npx",
"args": [
"minimax-mcp-tools"
],
"env": {
"MINIMAX_API_KEY": "your-minimax-api-key",
"MINIMAX_GROUP_ID": "your-minimax-group-id"
}
}
}
}3. Restart Claude Desktop for the changes to take effect