A Cloudflare-based visual recognition MCP that provides some visual capabilities to non-multimodal large language models such as DeepSeek
1 file for Codex and OpenCode: vision-mcp-worker AGENTS.md — 360 tokens loaded in every session.
AGENTS.md A 360 tok These files are xanzl/vision-mcp-worker'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.