JayceVane/visual-understanding

Multi-provider visual understanding MCP server + CLI — caption, OCR, Q&A, grounding (Zhipu GLM-V / OpenAI / Anthropic / any OpenAI-compatible endpoint)

Open on GitHub

1Stars on the repository

2Mods indexed here, across every type

15d agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

visual-understanding

JayceVane/visual-understanding

MCP server Claude CodeCodexCursor

Multi-provider visual understanding MCP server & CLI — caption, OCR, Q&A, grounding. Runs locally from the visual-understanding Python package.

1 15d ago A tokens not measured original MIT