glm-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| Z_AI_MODE | No | Platform: ZHIPU (China) or ZAI (International). | ZHIPU |
| Z_AI_API_KEY | No | Zhipu Coding Plan API key. Required if ZAI_MCP_API_KEY is not set. | |
| Z_AI_TIMEOUT | No | Request timeout in milliseconds. | 300000 |
| ZAI_MCP_API_KEY | No | Fallback alias for Z_AI_API_KEY. Auto-mapped if Z_AI_API_KEY is not set. | |
| GLM_VISION_CACHE | No | Enable result caching. | true |
| Z_AI_RETRY_COUNT | No | Maximum retries for retryable errors. | 2 |
| Z_AI_VISION_MODEL | No | Vision model ID. | glm-5v-turbo |
| GLM_VISION_CACHE_MAX | No | Max LRU cache entries. | 100 |
| GLM_VISION_CACHE_TTL | No | Cache TTL in seconds (7 days). | 604800 |
| GLM_IMAGE_MAX_SIZE_MB | No | Maximum image file size in megabytes. | 5 |
| GLM_VIDEO_MAX_SIZE_MB | No | Maximum video file size in megabytes. | 8 |
| Z_AI_VISION_MODEL_TOP_P | No | Nucleus sampling parameter. | 0.6 |
| Z_AI_VISION_MODEL_MAX_TOKENS | No | Max output tokens. | 32768 |
| Z_AI_VISION_MODEL_TEMPERATURE | No | Sampling temperature. | 0.8 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ui_to_artifactA | 将 UI 截图转换为代码、提示词、设计规范或自然语言描述。 仅在用户需要以下操作时使用:
不要用于:需提取的文字/代码、错误信息、技术图表、数据可视化。 |
| extract_text_from_screenshotA | 使用 OCR 从截图中提取和识别文字。专门用于代码、终端输出、文档和通用文本提取。 仅在用户需要以下操作时使用:
不要用于:UI 转 code、错误诊断、图表分析。 |
| diagnose_error_screenshotA | 解析错误弹窗、堆栈跟踪和日志截图,给出定位与修复建议。 仅在用户需要以下操作时使用:
不要用于:提取代码、UI 分析、图表解读。 |
| understand_technical_diagramA | 分析技术图表并生成结构化解读,覆盖架构图、流程图、UML、ER 图、序列图等。 仅在用户需要以下操作时使用:
不要用于:UI 截图、错误消息、数据可视化图表。 |
| analyze_data_visualizationA | 阅读仪表盘、统计图表,提炼趋势、异常与业务要点。 仅在用户需要以下操作时使用:
不要用于:技术架构图、UI 截图、错误诊断。 |
| ui_diff_checkA | 对比两张 UI 截图,识别视觉差异和实现偏差。专门用于 UI 质量保证和设计到实现的验证。 仅在用户需要以下操作时使用:
需要两张图:预期/参考图 与 实际/当前图。 |
| analyze_imageA | 通用图像理解能力,适配未被专项工具覆盖的视觉内容。 仅在用户需要以下操作时使用:
这是兜底工具,优先使用更专业的工具。 |
| analyze_videoA | 使用 AI 视觉模型分析视频内容。 仅在用户需要以下操作时使用:
支持本地文件与远程 URL,最大 8MB,支持 MP4/MOV/M4V 等格式。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/JJChou000/glm-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server