Image metadata reader (vision)
Generated from
mcp/patterns.registry.json— do not edit by hand; change the registry and runbun run patterns:build.
Index card — the docs below are the canonical explanation; deep-tier pattern pages additionally carry invariants and emulation notes.
Category: AI · Tier: light · Risk: medium — external LLM providers with quota limits
A vision-capable LLM proposes title, caption, alt text, keywords, and category for an uploaded image, which a human reviews and approves before anything persists.
When to use: Use when uploaded media needs AI-drafted metadata but a human must confirm every field before it is saved.
Docs
Code
Proof
Machine-readable record: ai-image-metadata in mcp/patterns.registry.json.