KOG123/visual-intelligence-mcp

An MCP server that provides image recognition for Codex / Claude Code. The main model (such as DeepSeek) handles reasoning and decision-making, while the task of viewing screens/screenshots is delegated to multimodal models.

23 files for Claude Code: openspec-apply-change, openspec-archive-change, openspec-bulk-archive-change, openspec-continue-change and 19 more .

2Stars on the repository
23Files it configures its agents with
—Tokens loaded in every session
1Agent configured

Settings

Skills

Commands

These files are KOG123/visual-intelligence-mcp's own configuration — they tell Claude Code 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.