MiniMax Vision MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MiniMax Vision MCP Server Describe what's happening in this image: /tmp/screenshot.png"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MiniMax Vision MCP Server
MCP server for MiniMax vision models โ analyze images through the
OpenAI-compatible POST /v1/chat/completions endpoint.
Features
๐ผ๏ธ Analyze images โ local files (png/jpg/jpeg/gif/webp/bmp) and remote HTTP(S) URLs
๐ง MiniMax-M3: image + video understanding, 1M context, adaptive thinking
๐๏ธ
temperaturefully configurable[0, 2](unlike some providers that lock it)๐ญ
thinkingflag โ enables adaptive thinking +reasoning_spliton M3โก Zero non-MCP dependencies, one-line
npxdeploy
Related MCP server: z_ai_vision_mcp_server_clone
Requirements
Node.js >= 18
A MiniMax platform API key (่ดฆๆท็ฎก็ โ ๆฅๅฃๅฏ้ฅ)
Install & run
cd minimax-vision-mcp-server
npm install
npm startEnvironment variables
Variable | Required | Default | Description |
| โ | โ | Your MiniMax API key. |
|
| Model: | |
|
| Override endpoint (for proxies). | |
|
| Default max output tokens. M3 supports up to 524288. |
Note: International users may use
https://api.minimaxi.com/v1as the base URL.
Claude Code / CC-Switch config
{
"mcpServers": {
"minimax-vision": {
"type": "stdio",
"command": "npx",
"args": ["-y", "minimax-vision-mcp-server"],
"env": {
"MINIMAX_API_KEY": "your-minimax-api-key",
"MINIMAX_MODEL": "MiniMax-M3"
}
}
}
}Tool: minimax_vision_understand
Parameter | Type | Required | Description |
| string | โ | Local image path or remote HTTP(S) URL. |
| string | โ | What to ask about the image. |
| number | Max output tokens. Default 8192. | |
| number | 0-2, default 1. | |
| bool | Enable adaptive thinking + reasoning split (M3). M2.x always think; ignored there. |
Why MiniMax for vision?
1M context on M3 โ analyze long documents alongside images
Native image + video understanding
Configurable temperature โ fine-grained control over determinism
Adaptive thinking โ reasoning on by default, splittable via
reasoning_split
Related projects
kimi-vision-mcp-server โ Moonshot Kimi
doubao-vision-mcp-server โ ByteDance Doubao
glm-vision-mcp-server โ Zhipu GLM
qwen-vision-mcp-server โ Alibaba Qwen
@kira4094/agnes-image-mcp-server โ Agnes Image (text-to-image)
License
MIT
Available Tools
1 toolminimax_vision_understandA
Analyze an image using MiniMax vision models. Supports local image files (png/jpg/jpeg/gif/webp/bmp) AND remote HTTP(S) URLs. Default model: MiniMax-M3. MiniMax-M3 supports image + video understanding, 1M context, adaptive thinking.
Inputs: image (required), prompt (required), thinking, max_tokens, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with another. The tool's purpose is clearly defined for image understanding.
The single tool name 'minimax_vision_understand' follows a clear verb_noun pattern, and with only one tool, naming consistency is trivially perfect.
A single tool feels thin for a server named 'Vision MCP Server', but it covers the core image understanding use case. It is borderline but not severely under-scoped.
The tool covers basic image understanding and supports multiple input formats, but lacks options for model selection or video understanding, despite the underlying model supporting video. Some common vision tasks like OCR or object detection are not present, but that may be out of scope.
Maintenance
Related MCP Connectors
MCP server for MiniMax H3 multimodal video generation
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
MCP server for Hailuo (MiniMax) AI video generation
MCP server for Qwen Image 3 AI image generation
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server for analyzing images using ModelScope's vision models. Supports both local files and URLs, enabling image content description and question answering.1488 npm10MIT
- FlicenseBqualityDmaintenanceOpenAI-compatible MCP server for running image analysis tools against your own vision model endpoint.76 npm-
- AlicenseNot gradedqualityDmaintenanceMCP server for analyzing images using multiple vision LLM providers (OpenCode, OpenAI, Anthropic, Google, and custom OpenAI-compatible endpoints). Provides tools to analyze single or multiple images, list providers, and test vision capabilities.MIT
- AlicenseNot gradedqualityCmaintenanceEnables image analysis via OpenAI-compatible vision APIs, supporting local files, URLs, and base64 inputs with intelligent tiling for high-resolution images. Provides a secure, configurable MCP stdio server for structured vision analysis.91 npm3MIT