Skip to main content

vision-augment

视觉增强 MCP —— 为无视觉能力的 LLM(如 DeepSeek、GLM)提供看图、OCR 与文档解析。当用户需要分析图片/截图内容、识别图片中的文字、解析 docx/pdf/pptx/xlsx/html 文档时使用。工具:mcp_vision_augment_vision(task_type=reasoning|ocr|document)、mcp_vision_augment_health(环境探测)、mcp_vision_augment_clear_cache。

Jump to install

Source facts

Repository
CaoMeiYouRen/vision-augment
Last source activity
August 11, 2026 at 18:41
Detected SKILL.md language
Chinese
Stars
0
Forks
0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.