How do I use MiniMax Vision MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MiniMax Vision MCP Describe this image: https://example.com/photo.jpg" 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

by wenjiaqi8255

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

MiniMax Vision MCP

将 MiniMax VL 多模态能力通过 MCP 暴露给 Claude Code（或其他 MCP 客户端），补足 DeepSeek v4 flash 等非多模态模型的读图能力。

功能

understand_image — 分析单张或多张图片，返回文字描述
支持本地文件路径、http(s) URL、base64 data URL
格式：JPEG、PNG、WebP、GIF
支持两种 MiniMax API 模式（通过 MINIMAX_ENDPOINT 切换）

Related MCP server: Image Parse MCP

前置条件

Python 3.10+
MiniMax API Key（开通了 VL 模型的 token plan）

快速开始

1. 安装

cd ~/Downloads/minimax-vision-mcp
pip install -e .

或用 uv（推荐）：

cd ~/Downloads/minimax-vision-mcp
uv pip install -e .

2. 配置 Claude Code

编辑 ~/.claude/settings.local.json（或项目的 .claude/settings.json），添加：

{
  "mcpServers": {
    "minimax-vision": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/Users/wenjiaqi/Downloads/minimax-vision-mcp",
        "minimax-vision-mcp"
      ],
      "env": {
        "MINIMAX_API_KEY": "your-api-key-here",
        "MINIMAX_ENDPOINT": "chat_completion"
      }
    }
  }
}

Claude Desktop 也兼容：上述 stdio 配置格式可直接用于 claude_desktop_config.json。

3. 重启 Claude Code

重启后，在对话中发送图片或图片路径，Claude 会自动调用 understand_image 工具来分析图片。

环境变量

变量	必需	默认值	说明
`MINIMAX_API_KEY`	✅	—	MiniMax API 密钥
`MINIMAX_API_HOST`	❌	`https://api.minimax.chat`	API 地址（中国区用 `https://api.minimaxi.com`）
`MINIMAX_MODEL`	❌	`minimax-vl-01`	VL 模型名（仅 `chat_completion` 模式）
`MINIMAX_ENDPOINT`	❌	`chat_completion`	API 模式：`chat_completion` 或 `coding_plan`

两种 API 模式

chat_completion（默认） 通用 MiniMax VL API，通过 /v1/text/chatcompletion_v2 调用，支持多图、system prompt、temperature 等参数。适用于标准 token plan。

coding_plan MiniMax Coding Plan 专有端点 /v1/coding_plan/vlm，仅支持单图 + prompt。如果你是 Coding Plan 用户可用此模式。

不确定用哪个？ 先试试 chat_completion（默认）。如果返回 404 或 auth 错误，切到 coding_plan。

使用示例

# 分析本地图片
understand_image(
    prompt="这张图片里有什么？请详细描述。",
    image_path="/Users/wenjiaqi/Downloads/photo.png"
)

# 分析网络图片
understand_image(
    prompt="Extract text from this image",
    image_url="https://example.com/screenshot.jpg"
)

# 多图对比
understand_image(
    prompt="Compare these two UI designs",
    image_paths=["/path/to/design1.png", "/path/to/design2.png"]
)

项目结构

minimax-vision-mcp/
├── pyproject.toml
├── README.md
└── src/
    └── minimax_vision_mcp/
        ├── __init__.py
        └── server.py          # MCP 服务器主文件

License

MIT

Available Tools

1 tool

understand_imageB

Analyze an image and return a text description. This is the ONLY tool that can 'see' image files. Supports local file paths, http(s) URLs, and base64 data URLs. Formats: JPEG, PNG, WebP, GIF.

ParametersJSON Schema

Name	Required	Default
`prompt`	No	Describe this image in detail.
`image_url`	No
`image_path`	No
`image_urls`	No
`max_tokens`	No
`image_paths`	No
`temperature`	No
`system_prompt`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description bears full responsibility. It discloses supported image sources (local paths, URLs, base64) and formats (JPEG, PNG, WebP, GIF). However, it does not mention error handling, authentication, or what happens with unsupported formats or missing images.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise at three sentences, with the main purpose front-loaded. It efficiently states the tool's unique capability. Minor improvement could be structural grouping of parameter types.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no schema descriptions, no annotations, and 8 parameters, the description is incomplete. It omits output format, parameter defaults, and usage constraints. The tool has an output schema, but its content is unknown; the description should at least hint at return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning the description must compensate. It only mentions image sources and formats, but does not explain any of the 8 parameters (e.g., prompt, max_tokens, temperature). The parameters remain opaque, failing to add value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool analyzes an image and returns a text description. It explicitly notes it is the only tool that can 'see' image files, providing strong differentiation even though no sibling tools are listed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a strong usage hint: 'This is the ONLY tool that can see image files.' This implicitly tells when to use it. However, it lacks explicit when-not-to-use guidance or alternatives, but given no siblings, this is acceptable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updatev0.1.0Jul 11, 2026
- First observedunderstand_image

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored 2026-07-11 02:16 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no ambiguity between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

The single tool name 'understand_image' follows a clear verb_noun pattern and is descriptive of its function.

Tool Count2/5

With only one tool, the server feels too limited for the implied scope of 'MiniMax Vision MCP'. A vision server would typically offer multiple capabilities.

Completeness2/5

The tool provides only image-to-text analysis. No other operations (e.g., object detection, metadata retrieval) are available, leaving significant gaps for a vision server.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

rostro AOAuth
dev.rostro
Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
Multimedia Processing Image & Video Processing Audio Processing
2
Artin0123-gemini-image-mcp-server
ai.smithery
Analyze images and videos with Gemini to get fast, reliable visual insights. Handle content from U…
Image & Video Processing Multimedia Processing
22
APICK AI A
app.apick
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
AI & Machine Learning Image & Video Processing
1511
Codex Imagem A
io.github.mcp-dir
Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits
AI & Machine Learning Image & Video Processing
81

Related MCP Servers

Vision MCP
Image & Video Processing Multimedia Processing
i-richardwang
A
license
A
quality
D
maintenance
Enables image analysis and understanding using Vision Language Models through OpenAI-compatible APIs. Supports analyzing images from URLs or local files with custom prompts.
Updated 9 months ago (2025-12-26 05:40 UTC)
1
2
MIT
Image Parse MCP
AI & Machine Learning Image & Video Processing
1617110693
A
license
A
quality
D
maintenance
Enables image analysis using any OpenAI-compatible vision API, supporting URLs, local files, or base64 input with custom prompts.
Updated 3 months ago (2026-06-18 14:31 UTC)
1
MIT
Look At Pic MCP
Image & Video Processing AI & Machine Learning
bbsteel
F
license
Not graded
quality
B
maintenance
Enables image analysis using GLM-4V multimodal model, supporting local files and base64 images with optional custom prompts.
Updated 3 months ago (2026-06-27 06:58 UTC)
-
mcp-image-analyzer
Image & Video Processing AI & Machine Learning
yunper-wang
A
license
A
quality
B
maintenance
Enables LLMs to analyze images via OpenAI-compatible multimodal models, supporting local files, base64, and URLs with safety validation and model selection.
Updated 2 months ago (2026-08-04 08:28 UTC)
1
MIT

MiniMax Vision MCP

功能

前置条件

快速开始

1. 安装

2. 配置 Claude Code

3. 重启 Claude Code

环境变量

两种 API 模式

使用示例

项目结构

License

Available Tools

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Vision MCP

Image Parse MCP

Look At Pic MCP

mcp-image-analyzer