MCP Servers

Specialized MiniMax Model Context Protocol (MCP) server designed for coding-plan users, featuring AI-powered search and vision analysis APIs optimized for code development workflows. Unlike the standard MiniMax-MCP, this version provides coding-specific tools (for examples: web_search and understand_image) that integrate seamlessly with MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to enhance your coding experience.

Documentation

• 中文文档

Quickstart with MCP Client

1. Get your API key from MiniMax.
2. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.
3. Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.

|Region| Global | Mainland | |:--|:-----|:-----| |MINIMAX_API_KEY| go get from MiniMax Global | go get from MiniMax | |MINIMAX_API_HOST| https://api.minimax.io | https://api.minimaxi.com |

Claude Desktop

Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:

{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": [
        "minimax-coding-plan-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_API_HOST": "api host, https://api.minimax.io | https://api.minimaxi.com"
      }
    }
  }
}

⚠️ Warning: The API key needs to match the host. If an error "API Error: invalid api key" occurs, please check your api host:

• Global Host：https://api.minimax.io
• Mainland Host：https://api.minimaxi.com

If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu in the top left and select "Enable Developer Mode".

Cursor

Go to Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server to add above config.

That's it. Your MCP client can now interact with MiniMax through these tools:

Transport

We support two transport types: stdio and sse. | stdio | SSE | |:-----|:-----| | Run locally | Can be deployed locally or in the cloud | | Communication through stdout | Communication through network | | Input: Supports processing local files or valid URL resources | Input: When deployed in the cloud, it is recommended to use URL for input |

Available Tools

| tool | description | |-|-| |web_search|Performs web searches and returns organic search results along with related search queries| |understand_image|Analyzes images with AI based on text prompts, extracts information and answers questions about images|

Release Notes

November 20, 2025

🆕 What's New

• Web Search: New web_search tool - perform web searches and get organic results with related search queries
• Vision Language Model: New understand_image tool - analyze images using AI based on text prompts

📈 Features

• web_search - Search the web and get structured results including titles, links, snippets, and related searches
• understand_image - Analyze images from URLs or local files, supporting JPEG, PNG, and WebP formats

FAQ

1. invalid api key

Please ensure your API key and API host are regionally aligned |Region| Global | Mainland | |:--|:-----|:-----| |MINIMAX_API_KEY| go get from MiniMax Global | go get from MiniMax | |MINIMAX_API_HOST| https://api.minimax.io | https://api.minimaxi.com |

2. spawn uvx ENOENT

Please confirm its absolute path by running this command in your terminal:

which uvx

Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx").

Example usage

⚠️ Warning: Using these tools may incur costs.

1. Web Search

Use the web_search tool to search for information on the web:

2. Image Analysis

Use the understand_image tool to analyze images with AI: