Give text models eyes: an MCP Server that uses OpenAI-compatible vision models (Tongyi Qianwen VL on ModelScope by default) to convert image files into textual descriptions, enabling text models such as DeepSeek and GLM to understand images. Runs locally over stdio and works out of the box with Claude Code / Opencode.
Latest release 0.0.2 · 3 Aug 2026
These files are me9rez/llm-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.
AGENTS.md A 566 tok