llm-vision-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TOOLS | No | Comma-separated whitelist of tools to enable (e.g., 'analyze_image,extract_text'). Leave empty to enable all. | |
| API_KEY | Yes | Provider API key. For ModelScope tokens, remove the 'ms-' prefix. | |
| BASE_URL | No | OpenAI-compatible API endpoint. | https://api-inference.modelscope.cn/v1 |
| MAX_TOKENS | No | Maximum number of tokens to generate (positive integer). | 32768 |
| TEMPERATURE | No | Sampling temperature (e.g., '0' or '0.5'). | 0.7 |
| VISION_MODEL | No | Vision model name. | Qwen/Qwen3-VL-8B-Instruct |
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 |
|---|---|
| analyze_imageC | 分析磁盘上的图片文件 / Analyze an image file on disk |
| extract_textB | 从磁盘图片中提取文字(OCR) / OCR an image file on disk |
| describe_uiB | 描述磁盘上 UI 图片文件 / Describe a UI screenshot file |
| diagnose_errorA | 诊断磁盘上错误图片文件 / Diagnose an error screenshot file |
| understand_diagramA | 解读流程图/架构图等图表 / Interpret a diagram image file |
| analyze_chartB | 分析数据图表中的趋势和洞察 / Analyze a chart image file |
| code_from_screenshotB | 从磁盘图片中提取代码 / Extract code from a screenshot file |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Most tools have clearly distinct purposes (OCR, UI description, error diagnosis, diagram interpretation, chart analysis, code extraction), but 'analyze_image' is a generic catch-all that could overlap with any of the specialized tools, creating potential misselection.
All tool names follow a consistent verb_noun pattern (analyze_image, extract_text, describe_ui, diagnose_error, understand_diagram, analyze_chart), with only 'code_from_screenshot' being a slight deviation but still fitting the overall style.
7 tools is a well-scoped count for a vision analysis server, covering common image tasks without unnecessary bloat or thinness.
The tool set covers general analysis, OCR, UI, errors, diagrams, charts, and code extraction, which is comprehensive for typical vision workflows. Minor gaps like image transformation or object detection exist but are not core to the server's implied purpose.