Vision bridge for text-only AI models - image analysis powered by Gemini API with MCP, CLI, and Codex skill support
Latest release v1.1.1 — v1.1.1 - Fix Lazy Import Scope, Health Check Warnings & Online API Verification · 6 Aug 2026
1 file for Codex and OpenCode: deepseek-vision-mcp AGENTS.md — 501 tokens loaded in every session.
AGENTS.md A 501 tok These files are tqctqc1/deepseek-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.