image-processing

Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.

Image message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen script

本地 Pillow 图片处理 MCP：12 工具（信息/缩放/裁剪/转换/压缩/旋转/翻转/缩略图/水印/特效/占位/叠加），离线零成本，经 dsh-mcp-client 接入 DSH。Local Pillow image MCP with 12 tools for DeepSeek Harness, offline & free. | Platforms: macOS/Windows/Linux (Python+Pillow)