atx-mcp server

atx-mcp

English | 日本語 | 简体中文

A deterministic (non-generative) asset transformation MCP server for general-purpose AI agents, written in Rust.

It executes editing intent — "level the horizon, crop to 16:9, brighten it up a touch" — as a declarative transform recipe, and tracks every result as an immutable revision. The original asset is never modified.

Tilt correction + auto levels + a look applied (a fully deterministic recipe) — left: input / right: output.

See docs/DESIGN.md for the full design.

Use cases

1. Eye-catch image for an article

"Straighten this photo and crop it to a 16:9, 1600px eye-catch. WebP."

importasset → detecttilt (the AI skips correction when it's already near-level) → applytransform (rotate → crop → resize → encode) → exportasset. The original is never touched, and the same recipe reproduces the same result every time.

1. Multiple sizes for social/CMS

"Generate the OGP, Instagram square, and thumbnail versions of this photo."

One original fans out into OGP 1200×630, Instagram 1080 square, and a 400px thumbnail in parallel. The same-recipe-same-revision idempotency means re-running never double-creates output; a one-word preset name works too.

1. Safe to publish

"Strip the location data for sure, but don't touch the colors."

stripmetadata (exif) removes EXIF including GPS while keeping the ICC profile intact. The AI can also warn ahead of time by checking hasgps from inspect_image.

1. Color and look adjustments

"Make just the sky bluer, leave everything else alone."

Covers curves / levels / hsl / whitebalance, the filmsoft preset, and importing your own .cube LUT with import_asset then applying it with lut.

1. Local (masked) adjustments

"Darken just the sky a bit, keep the ground as is."

generatemask builds a mask (gradient, luminosity range, or hue range); after wiring it into the adjustment, renderpreview with overlay:"mask" shows exactly where it will bite before you commit.

1. Layer compositing

"Blur a copy of this photo and blend it in at 50% screen for a soft glow."

The layers stack combines 16 blend modes, opacity, and masks to build reproducible composites like soft focus.

1. Watermarks, retouching, and perspective

"Stamp my logo in the corner, remove the power lines, and fix the converging verticals."

svg_overlay burns in a logo, clone/heal remove blemishes or wires by compositing both texture and tone, and perspective corrects converging verticals.

1. Reading documents (OCR pre-processing)

"Read this receipt photo for me." / "What does this slide say?"

detectdocument finds the page or screen and returns a perspective quad ready to paste, the ocrdocument preset (grayscale, auto levels, light sharpen) and trim concentrate the pixel budget on the text, and renderpreview with longedge:1568 hands the model an image it can actually read. No OCR engine is bundled: the model does the reading, atx only makes the pixels legible and reproducible. detecttextblocks answers the question that decides the rest — "will this text survive the downscale, and where do I cut?" — by returning the text blocks in reading order plus ready-to-paste crop bands. threshold (Otsu / Sauvola) and ocr_binarize exist for external OCR engines.

Shortened. The full README is on GitHub.