MCP服务器提供从本地文件、URL提取图像并转换为base64格式的功能,适用于LLM分析。
此 Skill 必须配置 API 密钥才能使用。
.env 中没有 XBY_APIKEY, 必须使用 AskUserQuestion 工具向用户询问 API 密钥scripts.config.set_api_key(api_key) 保存,然后继续处理你(大模型)是路由层,负责理解用户意图、选择工具、提取参数。代码只负责调用API。
text
用户输入 → 你选择工具 → 提取该工具需要的参数 → 调用 scripts.tools 中的函数 → 返回结果给用户
scripts.config.settings.api_key 为空,使用 AskUserQuestion 询问用户,拿到后调用 scripts.config.set_api_key(key) 保存scripts.tools 中的函数,例如 scripts.tools.search_schools(score='520', province='北京', category='综合')raw 数据整理后展示给用户根据用户意图选择对应的工具函数:
用户意图工具函数Extract and analyze images from local file paths. Supports visual content understanding, OCR text extraction, and object recognition for screenshots, photos, diagrams, and documents.scripts.tools.extract_image_from_fileExtract and analyze images from web URLs. Perfect for analyzing web screenshots, online photos, diagrams, or any image accessible via HTTP/HTTPS for visual content analysis and text extraction.scripts.tools.extract_image_from_urlExtract and analyze images from base64-encoded data. Ideal for processing screenshots from clipboard, dynamically generated images, or images embedded in applications without requiring file system access.scripts.tools.extract_image_from_base64
如果参数不完整,使用 AskUserQuestion 向用户询问缺失的参数。
工具描述:Extract and analyze images from local file paths. Supports visual content understanding, OCR text extraction, and object recognition for screenshots, photos, diagrams, and documents.
参数名称参数类型是否必填默认值描述file_pathstringtruePath to the image file to analyze (supports screenshots, photos, diagrams, and documents in PNG, JPG, GIF, WebP formats)resizebooleanfalsetrueFor backward compatibility only. Images are always automatically resized to optimal dimensions (max 512x512) for LLM analysismax_widthnumberfalse512.0For backward compatibility only. Default maximum width is now 512pxmax_heightnumberfalse512.0For backward compatibility only. Default maximum height is now 512px
工具描述:Extract and analyze images from web URLs. Perfect for analyzing web screenshots, online photos, diagrams, or any image accessible via HTTP/HTTPS for visual content analysis and text extraction.
参数名称参数类型是否必填默认值描述urlstringtrueURL of the image to analyze for visual content, text extraction, or object recognition (supports web screenshots, photos, diagrams)resizebooleanfalsetrueFor backward compatibility only. Images are always automatically resized to optimal dimensions (max 512x512) for LLM analysismax_widthnumberfalse512.0For backward compatibility only. Default maximum width is now 512pxmax_heightnumberfalse512.0For backward compatibility only. Default maximum height is now 512px
工具描述:Extract and analyze images from base64-encoded data. Ideal for processing screenshots from clipboard, dynamically generated images, or images embedded in applications without requiring file system access.
参数名称参数类型是否必填默认值描述base64stringtrueBase64-encoded image data to analyze (useful for screenshots, images from clipboard, or dynamically generated visuals)mime_typestringfalse"image/png"MIME type of the image (e.g., image/png, image/jpeg)resizebooleanfalsetrueFor backward compatibility only. Images are always automatically resized to optimal dimensions (max 512x512) for LLM analysismax_widthnumberfalse512.0For backward compatibility only. Default maximum width is now 512pxmax_heightnumberfalse512.0For backward compatibility only. Default maximum height is now 512px
工具函数返回 dict 对象:
result["raw"] - API 原始返回数据(JSON), 直接将此数据整理后展示给用户result["success"] - 是否成功(True/False)result["message"] - 状态消息text
xiaobenyang_gaokao_skill/
├── scripts/
│ ├── __init__.py
│ ├── config.py # 配置管理 + set_api_key()
│ ├── call_api.py # API 客户端 + call_api()
│ └── tools.py # 工具函数(直接调用)
├── requirements.txt
└── SKILL.md