为纯文本主模型提供多模态能力的MCP服务器,通过外包图像、视频和音频分析给外部多模态模型并回填文字结果。
Getting started
Add multimodal-proxy to your MCP-capable client — Claude Code, Cursor, Codex, and others — by following the setup at the source, which documents the exact command, configuration, and any required API keys.






