glm-understand-image

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

glm-understand-image

使用 GLM 视觉 MCP 服务器进行图像理解和分析。

Perform image understanding and analysis using GLM Vision MCP server.

执行流程（首次需要安装，后续直接步骤6调用）

Execution Flow (Installation required for first use, directly call step 6 afterwards)

步骤 1: 检查并安装依赖

Step 1: Check and Install Dependencies

1.1 检查 mcporter 是否可用

1.1 Check if mcporter is available

bash

npx -y mcporter --version

如果命令返回成功，说明 mcporter 可用，跳到步骤 2。

mcporter 可以直接通过 npx 使用，无需安装。

bash

npx -y mcporter --version

If the command returns successfully, mcporter is available, skip to Step 2.

mcporter can be used directly via npx without installation.

步骤 2: 检查 API Key 配置

Step 2: Check API Key Configuration

bash

cat ~/.openclaw/config/glm.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/glm.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, skip to Step 4.

步骤 3: 配置 API Key（如果未配置）

Step 3: Configure API Key (if not configured)

3.2 如果没有找到 Key，向用户索要

3.2 Request Key from User if Not Found

询问用户提供智谱 API Key。

如果用户没有智谱 API Key，可以访问 https://www.bigmodel.cn/glm-coding?ic=OOKF4KGGTW 购买。

Ask the user to provide Zhipu API Key.

If the user does not have a Zhipu API Key, they can purchase it at https://www.bigmodel.cn/glm-coding?ic=OOKF4KGGTW.

3.3 保存 API Key

3.3 Save API Key

bash

mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/glm.json << EOF
{
  "api_key": "API密钥"
}
EOF

bash

mkdir -p ~/.openclaw/config
cat > ~/.openclaw/config/glm.json << EOF
{
  "api_key": "API_KEY"
}
EOF

步骤 4: 添加 MCP 服务器

Step 4: Add MCP Server

使用 mcporter 添加 GLM 视觉 MCP 服务器：

bash

mcporter config add glm-vision \
  --command "npx -y @z_ai/mcp-server" \
  --env Z_AI_API_KEY="your-key" \
  --env Z_AI_MODE="ZHIPU" \
  --env HOME="$PWD"

注意：将

your-key

替换为实际的智谱 API Key。

HOME

环境变量设置为当前工作目录以避免日志文件权限问题。

Use mcporter to add GLM Vision MCP server:

bash

mcporter config add glm-vision \
  --command "npx -y @z_ai/mcp-server" \
  --env Z_AI_API_KEY="your-key" \
  --env Z_AI_MODE="ZHIPU" \
  --env HOME="$PWD"

Note: Replace

your-key

with the actual Zhipu API Key. Set the

HOME

environment variable to the current working directory to avoid log file permission issues.

步骤 5: 测试连接

Step 5: Test Connection

bash

mcporter list

确认

glm-vision

服务器已成功添加。

bash

mcporter list

Confirm that the

glm-vision

server has been successfully added.

步骤 6: 使用 MCP 处理图像

Step 6: Use MCP to Process Images

6.1 准备图片

6.1 Prepare Images

将图片放到可访问路径，例如：

~/.openclaw/workspace/images/图片名.jpg

或者使用 URL

Place images in an accessible path, for example:

~/.openclaw/workspace/images/image-name.jpg

Or use a URL

6.2 使用 mcporter 调用 MCP 工具

6.2 Call MCP Tool Using mcporter

使用 mcporter 调用 MCP 服务：

bash

mcporter call glm-vision.analyze_image prompt="<对图片的提问>" image_source="<图片路径或URL>"

示例：

bash

undefined

Call the MCP service using mcporter:

bash

mcporter call glm-vision.analyze_image prompt="<Question about the image>" image_source="<Image path or URL>"

Examples:

bash

undefined

描述图片内容

Describe image content

mcporter call glm-vision.analyze_image prompt="详细描述这张图片的内容" image_source="~/image.jpg"

mcporter call glm-vision.analyze_image prompt="Describe the content of this image in detail" image_source="~/image.jpg"

使用 URL

Use URL

mcporter call glm-vision.analyze_image prompt="这张图片展示了什么？" image_source="https://example.com/image.jpg"

mcporter call glm-vision.analyze_image prompt="What does this image show?" image_source="https://example.com/image.jpg"

提取图片中的文字

Extract text from image

mcporter call glm-vision.extract_text_from_screenshot image_source="~/screenshot.png"

诊断错误截图

Diagnose error screenshot

mcporter call glm-vision.diagnose_error_screenshot prompt="分析这个错误" image_source="~/error.png"

undefined

mcporter call glm-vision.diagnose_error_screenshot prompt="Analyze this error" image_source="~/error.png"

undefined

6.3 API 参数说明

6.3 API Parameter Description

参数	说明	类型
image_source	图片路径或 URL	string (必填)
prompt	对图片的提问	string (必填)

Parameter	Description	Type
image_source	Image path or URL	string (Required)
prompt	Question about the image	string (Required)

支持的工具

Supported Tools

重要提示：如果出现问题以官方说明为准 官方版说明： https://docs.bigmodel.cn/cn/coding-plan/mcp/vision-mcp-server

GLM 视觉 MCP 服务器提供以下工具：

```
ui_to_artifact
```
- 将 UI 截图转换为代码、提示词、设计规范或自然语言描述
```
extract_text_from_screenshot
```
- 使用先进的 OCR 能力从截图中提取和识别文字
```
diagnose_error_screenshot
```
- 解析错误弹窗、堆栈和日志截图，给出定位与修复建议
```
understand_technical_diagram
```
- 针对架构图、流程图、UML、ER 图等技术图纸生成结构化解读
```
analyze_data_visualization
```
- 阅读仪表盘、统计图表，提炼趋势、异常与业务要点
```
ui_diff_check
```
- 对比两张 UI 截图，识别视觉差异和实现偏差
```
analyze_image
```
- 通用图像理解能力，适配未被专项工具覆盖的视觉内容
```
video_analysis
```
- 支持 MP4/MOV/M4V 等格式的视频场景解析，抓取关键帧、事件与要点

Important Note: Refer to official documentation if issues occur Official Documentation: https://docs.bigmodel.cn/cn/coding-plan/mcp/vision-mcp-server

GLM Vision MCP server provides the following tools:

```
ui_to_artifact
```
- Convert UI screenshots into code, prompts, design specifications, or natural language descriptions
```
extract_text_from_screenshot
```
- Extract and recognize text from screenshots using advanced OCR capabilities
```
diagnose_error_screenshot
```
- Parse error pop-ups, stack traces, and log screenshots to provide localization and repair suggestions
```
understand_technical_diagram
```
- Generate structured interpretations for technical diagrams such as architecture diagrams, flowcharts, UML, ER diagrams, etc.
```
analyze_data_visualization
```
- Read dashboards and statistical charts to extract trends, anomalies, and business key points
```
ui_diff_check
```
- Compare two UI screenshots to identify visual differences and implementation deviations
```
analyze_image
```
- General image understanding capability, suitable for visual content not covered by specialized tools
```
video_analysis
```
- Support video scene analysis for formats like MP4/MOV/M4V, capture key frames, events, and key points

MCP 配置

MCP Configuration

MCP 服务器名称：

glm-vision

MCP 服务器配置：

@z_ai/mcp-server

环境变量：

```
Z_AI_API_KEY
```
- 智谱 API Key（必需）
```
Z_AI_MODE
```
- 服务平台选择，默认为
```
ZHIPU
```

MCP Server Name:

glm-vision

MCP Server Configuration:

@z_ai/mcp-server

Environment Variables:

```
Z_AI_API_KEY
```
- Zhipu API Key (Required)
```
Z_AI_MODE
```
- Service platform selection, default is
```
ZHIPU
```