1. Home
  2. Servers
  3. AI Models & Agents
  4. MiniMax MCP

Server profile

MiniMax MCP

MiniMax MCP exposes MiniMax media APIs to compatible AI clients for speech, voice work, images, video, and music. It supports local stdio use and SSE deployment, with region-specific API credentials and configurable resource output.

View repositoryInstall & configure

Server facts

MiniMax MCP

Tech

Runtime / language
pythonPython
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
1,590
Last commit
Data as of

Tags

  • Image Generation
  • Minimax
  • Music Generation
  • Text To Speech
  • Video Generation
  • Voice Cloning

Overview

MiniMax MCP is MiniMax's official integration for exposing media generation APIs to MCP-compatible assistants. The supplied input describes text-to-speech, voice cloning, image generation, video creation, and video task status checks. The README also names music generation and prompt-based voice design, while the structured tool inventory includes audio playback and image-to-video conversion. These capabilities let an assistant coordinate several media tasks through a common connection rather than requiring a separate integration for each format. Supported clients mentioned in the README include Claude Desktop, Cursor, Windsurf, and OpenAI Agents.

Setup uses uvx and a MiniMax API key, with environment settings for the regional API host, local output path, and resource mode. The README stresses that a key must match its region: global and mainland accounts use different hosts, and mismatches cause authentication errors. Resources can be returned as URLs or downloaded locally, with URL mode described as the default. Stdio supports local files and URL inputs, while cloud SSE deployment is better suited to URL-based inputs. The README warns that tool use may incur costs. It also recommends a separate official CLI for newer models and additional capabilities. Users should therefore choose this MCP integration for its documented tool access while checking regional configuration and generation costs before starting media jobs.

Install & configure

Requirements

  • uv with uvx available
  • A MiniMax API key matching the selected regional host
  • An MCP-compatible client
Documented launch / install command
uvx minimax-mcp -y

The command follows the README's Claude Desktop configuration. Windows Claude Desktop may require Developer Mode. SSE is supported, but a ready-to-use SSE endpoint is not stated in the README.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "MiniMax-MCP": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "<your region-specific MiniMax API key>",
        "MINIMAX_MCP_BASE_PATH": "<local directory for generated output>",
        "MINIMAX_API_HOST": "<matching regional host: https://api.minimax.io or https://api.minimaxi.com>",
        "MINIMAX_API_RESOURCE_MODE": "<url or local; url is the default>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "MiniMax-MCP": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "<your region-specific MiniMax API key>",
        "MINIMAX_MCP_BASE_PATH": "<local directory for generated output>",
        "MINIMAX_API_HOST": "<matching regional host: https://api.minimax.io or https://api.minimaxi.com>",
        "MINIMAX_API_RESOURCE_MODE": "<url or local; url is the default>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "MiniMax-MCP": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "<your region-specific MiniMax API key>",
        "MINIMAX_MCP_BASE_PATH": "<local directory for generated output>",
        "MINIMAX_API_HOST": "<matching regional host: https://api.minimax.io or https://api.minimaxi.com>",
        "MINIMAX_API_RESOURCE_MODE": "<url or local; url is the default>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "MiniMax-MCP": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "<your region-specific MiniMax API key>",
        "MINIMAX_MCP_BASE_PATH": "<local directory for generated output>",
        "MINIMAX_API_HOST": "<matching regional host: https://api.minimax.io or https://api.minimaxi.com>",
        "MINIMAX_API_RESOURCE_MODE": "<url or local; url is the default>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "MiniMax-MCP": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "<your region-specific MiniMax API key>",
        "MINIMAX_MCP_BASE_PATH": "<local directory for generated output>",
        "MINIMAX_API_HOST": "<matching regional host: https://api.minimax.io or https://api.minimaxi.com>",
        "MINIMAX_API_RESOURCE_MODE": "<url or local; url is the default>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata and repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
text_to_audioSynthesize speech with a selected voice and save audio output; API charges may apply.
list_voicesList available voices; the supplied tool data restricts support to https://api.minimax.chat.
play_audioPlay a WAV or MP3 audio file, excluding video playback.
voice_cloneCreate a cloned voice from an audio file; initial use of new voices may incur charges.
text_to_imageCreate images from descriptive text through the MiniMax API.
generate_videoStart prompt-based video creation through MiniMax.
image_to_videoGenerate video using an image as input.
query_video_generationCheck the state of a video-generation task.
music_generationCreate music using descriptive instructions and supplied lyrics.
voice_designCreate a custom voice from a description and preview text.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Generate spoken audio using a chosen voice.
  • Clone or design a voice for a media workflow.
  • Create images or videos from descriptive prompts.
  • Check video-generation progress from an assistant.
  • Generate music from a prompt and lyrics.

Strengths

  • Combines several MiniMax media-generation capabilities in one integration.
  • Supports both stdio and SSE deployment.
  • Offers URL output or local resource downloads.

Limitations

  • API calls may incur costs.
  • API keys and hosts must match the account region.
  • The structured list_voices tool description limits that tool to a specific API host.

Frequently asked questions

The README highlights regional mismatches: global keys use https://api.minimax.io and mainland keys use https://api.minimaxi.com.

Yes. MINIMAX_API_RESOURCE_MODE selects url or local, and url is the documented default.

Yes. The README lists music_generation and voice_design in its available tools.

The README warns that using the generation tools may incur costs; exact prices are not stated.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

ElevenLabs MCP

AI Models & Agents

ElevenLabs MCP brings the vendor's speech and audio services into assistant workflows. This official integration supports voice work and transcription, with outputs delivered as files, MCP resources, or both.

pythonstdio1,535 GitHub stars

Just Prompt

AI Models & Agents

Just Prompt lets an MCP assistant consult several language models and preserve their answers. Alongside parallel prompting, it offers a panel workflow in which a designated model makes a decision after reviewing other responses.

pythonstdio739 GitHub stars

DeepSeek MCP Server

AI Models & Agents

DeepSeek MCP Server exposes DeepSeek V4 generation and account utilities to MCP clients. It offers chat, fill-in-the-middle completion, model discovery, balance checks, and in-process conversation management.

nodestdio353 GitHub stars

mcp-sequentialthinking-tools

AI Models & Agents

mcp-sequentialthinking-tools records stepwise reasoning with session history, branches, and revision metadata. It validates model-authored tool plans against a supplied tool list rather than discovering or choosing tools itself.

nodestdio587 GitHub stars