A Model Context Protocol (MCP) server that provides vision capabilities to analyze image and video
Latest release v0.0.7 · 4 Apr 2026
2 files for Codex, OpenCode and Claude Code: ai-vision-mcp AGENTS.md, ai-vision-mcp CLAUDE.md — 4,139 tokens loaded in every session.
AGENTS.md A 4,136 tok CLAUDE.md A 3 tok These files are tan-yong-sheng/ai-vision-mcp's own configuration — they tell Codex, OpenCode and Claude Code 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.