vision-analysis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Vision Analysis

视觉分析

Analyze images using the MiniMax

MiniMax_understand_image

MCP tool available in the MiniMax Token Plan.

使用MiniMax Token Plan中提供的MiniMax

MiniMax_understand_image

MCP工具分析图像。

Prerequisites

前提条件

MiniMax Token Plan subscription with valid
```
MINIMAX_API_KEY
```
MiniMax MCP configured (
```
MiniMax_understand_image
```
tool available)

订阅MiniMax Token Plan并拥有有效的
```
MINIMAX_API_KEY
```
已配置MiniMax MCP（可使用
```
MiniMax_understand_image
```
工具）

If MCP tool is not configured

若未配置MCP工具

Step 1: The agent should fetch setup instructions from: https://platform.minimaxi.com/docs/token-plan/mcp-guide

Step 2: Detect the user's environment (OpenCode, Cursor, Claude Code, etc.) and output the exact commands needed. Common examples:

OpenCode — add to

~/.config/opencode/opencode.json

package.json

json

{
  "mcp": {
    "MiniMax": {
      "type": "local",
      "command": ["uvx", "minimax-coding-plan-mcp", "-y"],
      "environment": {
        "MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
        "MINIMAX_API_HOST": "https://api.minimaxi.com"
      },
      "enabled": true
    }
  }
}

Claude Code:

bash

claude mcp add -s user MiniMax --env MINIMAX_API_KEY=your-key --env MINIMAX_API_HOST=https://api.minimaxi.com -- uvx minimax-coding-plan-mcp -y

Cursor — add to MCP settings:

json

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

Step 3: After configuration, tell the user to restart their app and verify with

/mcp

Important: If the user does not have a MiniMax Token Plan subscription, inform them that the

understand_image

tool requires one — it cannot be used with free or other tier API keys.

步骤1： Agent应从以下链接获取设置说明： https://platform.minimaxi.com/docs/token-plan/mcp-guide

步骤2： 检测用户的环境（OpenCode、Cursor、Claude Code等）并输出所需的准确命令。常见示例：

OpenCode — 添加至

~/.config/opencode/opencode.json

或

package.json

：

json

{
  "mcp": {
    "MiniMax": {
      "type": "local",
      "command": ["uvx", "minimax-coding-plan-mcp", "-y"],
      "environment": {
        "MINIMAX_API_KEY": "YOUR_TOKEN_PLAN_KEY",
        "MINIMAX_API_HOST": "https://api.minimaxi.com"
      },
      "enabled": true
    }
  }
}

Claude Code：

bash

claude mcp add -s user MiniMax --env MINIMAX_API_KEY=your-key --env MINIMAX_API_HOST=https://api.minimaxi.com -- uvx minimax-coding-plan-mcp -y

Cursor — 添加至MCP设置：

json

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

步骤3： 配置完成后，告知用户重启应用并通过

/mcp

命令验证配置。

重要提示： 若用户未订阅MiniMax Token Plan，需告知其

understand_image

工具需要该订阅，无法使用免费或其他层级的API密钥。

Analysis Modes

分析模式

Mode	When to use	Prompt strategy
`describe`	General image understanding	Ask for detailed description
`ocr`	Text extraction from screenshots, documents	Ask to extract all text verbatim
`ui-review`	UI mockups, wireframes, design files	Ask for design critique with suggestions
`chart-data`	Charts, graphs, data visualizations	Ask to extract data points and trends
`object-detect`	Identify objects, people, activities	Ask to list and locate all elements

模式	使用场景	提示策略
`describe`	通用图像理解	请求生成详细描述
`ocr`	从截图、文档中提取文本	请求逐字提取所有文本
`ui-review`	UI原型图、线框图、设计文件	请求提供设计评估及改进建议
`chart-data`	图表、图形、数据可视化	请求提取数据点和趋势
`object-detect`	识别物体、人物、活动	请求列出并定位所有元素

Workflow

工作流程

Step 1: Auto-detect image

步骤1：自动检测图像

The skill triggers automatically when a message contains an image file path or URL with extensions:

.jpg

.jpeg

.png

.gif

.webp

.bmp

.svg

Extract the image path from the message.

当消息包含带有以下扩展名的图片文件路径或URL时，该技能自动触发：

.jpg

、

.jpeg

、

.png

、

.gif

、

.webp

、

.bmp

、

.svg

从消息中提取图片路径。

Step 2: Select analysis mode and call MCP tool

步骤2：选择分析模式并调用MCP工具

Use the

MiniMax_understand_image

tool with a mode-specific prompt:

describe:

Provide a detailed description of this image. Include: main subject, setting/background,
colors/style, any text visible, notable objects, and overall composition.

ocr:

Extract all text visible in this image verbatim. Preserve structure and formatting
(headers, lists, columns). If no text is found, say so.

ui-review:

You are a UI/UX design reviewer. Analyze this interface mockup or design. Provide:
(1) Strengths — what works well, (2) Issues — usability or design problems,
(3) Specific, actionable suggestions for improvement. Be constructive and detailed.

chart-data:

Extract all data from this chart or graph. List: chart title, axis labels, all
data points/series with values if readable, and a brief summary of the trend.

object-detect:

List all distinct objects, people, and activities you can identify. For each,
describe what it is and its approximate location in the image.

使用带有模式特定提示的

MiniMax_understand_image

工具：

describe模式：

Provide a detailed description of this image. Include: main subject, setting/background,
colors/style, any text visible, notable objects, and overall composition.

ocr模式：

Extract all text visible in this image verbatim. Preserve structure and formatting
(headers, lists, columns). If no text is found, say so.

ui-review模式：

You are a UI/UX design reviewer. Analyze this interface mockup or design. Provide:
(1) Strengths — what works well, (2) Issues — usability or design problems,
(3) Specific, actionable suggestions for improvement. Be constructive and detailed.

chart-data模式：

Extract all data from this chart or graph. List: chart title, axis labels, all
data points/series with values if readable, and a brief summary of the trend.

object-detect模式：

List all distinct objects, people, and activities you can identify. For each,
describe what it is and its approximate location in the image.

Step 3: Present results

步骤3：呈现结果

Return the analysis clearly. For

describe

, use readable prose. For

ocr

, preserve structure. For

ui-review

, use a structured critique format.

清晰返回分析结果。对于

describe

模式，使用易读的散文式表述；对于

ocr

模式，保留文本结构；对于

ui-review

模式，使用结构化的评估格式。

Output Format Example

输出格式示例

For describe mode:

undefined

describe模式示例：

undefined

Image Description

[Detailed description of the image contents...]


For ocr mode:

[Detailed description of the image contents...]


ocr模式示例：

Extracted Text

[Preserved text structure from the image]


For ui-review mode:

[Preserved text structure from the image]


ui-review模式示例：

UI Design Review

Strengths

Issues

Suggestions

undefined

undefined

Notes

注意事项

Images up to 20MB supported (JPEG, PNG, GIF, WebP)
Local file paths work if MiniMax MCP is configured with file access

The

MiniMax_understand_image

tool is provided by the

minimax-coding-plan-mcp

package

支持最大20MB的图片（JPEG、PNG、GIF、WebP格式）
若MiniMax MCP配置了文件访问权限，本地文件路径可正常使用

MiniMax_understand_image

工具由

minimax-coding-plan-mcp

包提供