MCP server that gives text-only LLMs vision capability via vision models (e.g. Xiaomi MiMo-V2.5), with a WebUI config panel
1 file for Codex and OpenCode: mimo-vision-mcp AGENTS.md — 345 tokens loaded in every session.
AGENTS.md A 345 tok These files are mikulovesuki/mimo-vision-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.