Image Kit (upload → AI pipeline → adjust → approve, persists nothing)
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: Toolkits · Tier: light · Risk: low — no persistence of uploaded media, vision-call cost is the main concern
A single-page toolkit that chains an AI metadata reader, frame-cropper, and embedder on one uploaded image, then discards the upload after an honest approval terminal.
When to use: Use as a reference for building a stateless, multi-tool AI workflow that never persists user-uploaded media.
Docs
Code
Proof
Machine-readable record: toolkits-image-kit in mcp/patterns.registry.json.