minimax-understand-image
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chineseminimax-understand-image
minimax-understand-image
使用 MiniMax MCP 服务器进行图像理解和分析。
Use MiniMax MCP server for image understanding and analysis.
执行流程(首次需要安装,后续直接步骤4调用)
Execution Process (Installation required for first use, directly call at step 4 for subsequent uses)
步骤 1: 检查并安装依赖
Step 1: Check and install dependencies
1.1 检查 uvx 是否可用
1.1 Check if uvx is available
bash
which uvx如果不存在,安装 uv:
方法 1: 使用官方安装脚本(推荐)
bash
curl -LsSf https://astral.sh/uv/install.sh | sh方法 2: 使用国内镜像加速(如果官方脚本下载失败)
临时使用清华镜像源安装:
bash
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
curl -LsSf https://astral.sh/uv/install.sh | sh或者临时使用阿里云镜像源:
bash
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
curl -LsSf https://astral.sh/uv/install.sh | shbash
which uvxIf it does not exist, install uv:
Method 1: Use official installation script (recommended)
bash
curl -LsSf https://astral.sh/uv/install.sh | shMethod 2: Use domestic mirror for acceleration (if official script download fails)
Temporarily use Tsinghua mirror source for installation:
bash
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
curl -LsSf https://astral.sh/uv/install.sh | shOr temporarily use Alibaba Cloud mirror source:
bash
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
curl -LsSf https://astral.sh/uv/install.sh | sh1.2 检查 MCP 服务器是否已安装
1.2 Check if MCP server is installed
bash
uvx minimax-coding-plan-mcp --help执行命令判断是否MCP服务器已安装, 如果安装了跳到步骤 2。
bash
uvx minimax-coding-plan-mcp --helpRun the command to determine if the MCP server is installed, jump to Step 2 if it is already installed.
1.3 安装 MCP 服务器(如果未安装)
1.3 Install MCP server (if not installed)
方法 1: 使用默认源安装
bash
uvx install minimax-coding-plan-mcp方法 2: 使用国内镜像加速(如果默认源下载失败)
临时使用清华镜像源:
bash
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
uvx install minimax-coding-plan-mcp或者临时使用阿里云镜像源:
bash
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
uvx install minimax-coding-plan-mcpMethod 1: Install with default source
bash
uvx install minimax-coding-plan-mcpMethod 2: Use domestic mirror for acceleration (if default source download fails)
Temporarily use Tsinghua mirror source:
bash
export UV_INDEX_URL="https://pypi.tuna.tsinghua.edu.cn/simple"
uvx install minimax-coding-plan-mcpOr temporarily use Alibaba Cloud mirror source:
bash
export UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
uvx install minimax-coding-plan-mcp步骤 2: 检查 API Key 配置
Step 2: Check API Key configuration
bash
cat ~/.openclaw/config/minimax.json 2>/dev/null | python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('api_key', ''))"如果返回非空的 API Key,跳到步骤 4。
bash
cat ~/.openclaw/config/minimax.json 2>/dev/null | python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('api_key', ''))"If a non-empty API Key is returned, jump to Step 4.
步骤 3: 配置 API Key(如果未配置)
Step 3: Configure API Key (if not configured)
3.1 尝试从 ~/.openclaw/agents/main/agent/auth-profiles.json 中的配置文件中获取
3.1 Try to get from the configuration file at ~/.openclaw/agents/main/agent/auth-profiles.json
根据返回的判断:
- 名称包含 "minimax" 或 "MiniMax"
找到匹配的 Key 后,询问用户确认是否使用。
Judge based on the returned result:
- The name contains "minimax" or "MiniMax"
After finding the matching Key, ask the user for confirmation to use it.
3.2 如果没有找到 Key,向用户索要
3.2 If no Key is found, ask the user for it
直接询问用户提供 MiniMax API Key。
如果未购买MiniMax,购买地址为: https://platform.minimaxi.com/subscribe/coding-plan?code=GjuAjhGKqQ&source=link
Directly ask the user to provide MiniMax API Key.
If you have not purchased MiniMax, the purchase link is: https://platform.minimaxi.com/subscribe/coding-plan?code=GjuAjhGKqQ&source=link
3.3 保存 API Key
3.3 Save API Key
bash
mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/minimax.json << EOF
{
"api_key": "API密钥",
"output_path": "~/.openclaw/workspace/minimax-output"
}
EOFbash
mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/minimax.json << EOF
{
"api_key": "API密钥",
"output_path": "~/.openclaw/workspace/minimax-output"
}
EOF步骤 4: 使用 MCP 处理图像
Step 4: Process images with MCP
4.1 准备图片
4.1 Prepare the image
将图片放到可访问路径,例如:
~/.openclaw/workspace/images/图片名.jpg- 或者使用 URL
Put the image in an accessible path, for example:
~/.openclaw/workspace/images/your-image-name.jpg- Or use a URL
4.2 调用 understand_image
4.2 Call understand_image
使用脚本调用 MCP 服务:
bash
python3 {curDir}/scripts/understand_image.py <图片路径或URL> "<对图片的提问>"示例:
bash
undefinedCall the MCP service with the script:
bash
python3 {curDir}/scripts/understand_image.py <image path or URL> "<question about the image>"Example:
bash
undefined描述图片内容
Describe image content
python3 {curDir}/scripts/understand_image.py ~/image.jpg "详细描述这张图片的内容"
python3 {curDir}/scripts/understand_image.py ~/image.jpg "Describe the content of this image in detail"
使用 URL
Use URL
python3 {curDir}/scripts/understand_image.py "https://example.com/image.jpg "这张图片展示了什么?"
undefinedpython3 {curDir}/scripts/understand_image.py "https://example.com/image.jpg" "What does this image show?"
undefined4.3 API 参数说明
4.3 API Parameter Description
| 参数 | 说明 | 类型 |
|---|---|---|
| image | 图片路径或 URL | string (必填) |
| prompt | 对图片的提问 | string (必填) |
| Parameter | Description | Type |
|---|---|---|
| image | Image path or URL | string (required) |
| prompt | Question about the image | string (required) |
脚本说明
Script Description
脚本位置:
{curDir}/scripts/understand_image.py功能:
- 优先从环境变量 读取 API Key,如果没有则从
MINIMAX_API_KEY读取~/.openclaw/config/minimax.json - 通过 stdio 模式启动 MCP 服务器
- 发送 JSON-RPC 请求调用 工具
understand_image - 返回格式化的 JSON 结果
错误处理:
- API Key 未配置时提示错误
- uvx 未安装时提示安装命令
- MCP 服务器错误时显示 stderr 输出
Script location:
{curDir}/scripts/understand_image.pyFeatures:
- First read API Key from environment variable , if not present, read from
MINIMAX_API_KEY~/.openclaw/config/minimax.json - Start MCP server in stdio mode
- Send JSON-RPC request to call tool
understand_image - Return formatted JSON result
Error Handling:
- Prompt error when API Key is not configured
- Prompt installation command when uvx is not installed
- Display stderr output when MCP server encounters an error