A local image-recognition MCP that gives pure-text models such as DeepSeek visual capabilities (OCR, detection, segmentation, and zero-shot processing), entirely locally.
Latest release v2.3.0 — v2.3.0：本地识图 MCP——DeepSeek 看图 + 多图支持（OCR / 检测 / 分割 / 对比） · 9 Aug 2026
1 file for Codex and OpenCode: deepvision-local-mcp AGENTS.md — 674 tokens loaded in every session.
AGENTS.md A 674 tok These files are Yuhang-uestc/deepvision-local-mcp's own configuration — they tell Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.