# hanzo_vision — Multimodal UI, Screenshot & Document OCR

> Extracts structured JSON, tables, layout coordinates, and design tokens from screenshots, diagrams, and PDF documents.

- Type: Tool
- Publisher: hanzo
- Category: Multimodal
- Shop: Not a shop listing

## Links

- [Source](https://github.com/hanzoai/mcp)

---

Page: https://hanzo.market/l/lst_tool_hanzo_vision · Every listing: https://hanzo.market/llms.txt