About Reprise
Reprise is a remote MCP server that separates flat AI-generated designs into editable layers and measures how closely they are reproduced. It is for design workflows that need to revise or adapt existing artwork while checking fidelity.
Key features
- 01Separates flat designs into editable layers
- 02Detects design elements and text bounds
- 03Measures reproduction fidelity
- 04Exports layered SVG and transparent PNGs
- 05Supports manual element maps
Use cases
- 01Revise text or colors in a finished design
- 02Create campaign variants from one layout
- 03Check a reproduction against its original
MCP support
The remote MCP server exposes `reproduce`, `autodetect`, and `diagnose` tools to MCP clients over streamable HTTP or SSE. It accepts images by HTTP(S) URL or base64 data URL.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/httpclaude mcp add --transport http reprise https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http{"mcpServers":{"reprise":{"type":"http","url":"https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"}}}Open in Cursor{"servers":{"reprise":{"type":"http","url":"https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"}}}Open in VS Code{"mcpServers":{"reprise":{"type":"http","url":"https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"}}}{"mcpServers":{"reprise":{"serverUrl":"https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3| Parameter | Type | Required | Description |
|---|---|---|---|
| image | string | No | The source design image as an http(s) URL or a base64 data URL. |
Details
From the project READMEReprise — un-flatten any flat AI design into editable layers
You made a great design with AI. Then you needed to change one word — and you couldn't, because it's a flat PNG.
Reprise turns that finished, flat AI design (ChatGPT / Midjourney / Claude / etc.) back into editable layers and rebuilds it bit-perfect — and it returns a measured fidelity score, so you can verify the reproduction instead of trusting a claim. Reproducing runs locally and free; from there you can remix one design into a whole campaign.
It's built for agents, too: this repo is a remote MCP server, so Claude / Cursor / any MCP client can call reproduce / autodetect / diagnose directly.
Try it now (no signup)
Browser: open https://tepesama-reprise-mcp.hf.space/ → the “Try it” tab → drop a flat design (or click the sample). You'll see it un-flattened into layers, plus the fidelity score.
From your agent (MCP):
claude mcp add --transport http reprise https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http
Endpoints: /gradio_api/mcp/http (streamable-HTTP) · /gradio_api/mcp/sse (SSE) · /gradio_api/mcp/schema
Listed on the official MCP registry as design.reprise/reprise.
Tools
| Tool | What it does |
|---|---|
reproduce(image) | Un-flatten a flat design into editable layers and reproduce it bit-perfect. Returns a fidelity score (MAE / PSNR / exact-match % / stray px). |
autodetect(image) | Detect the elements (subjects and text) in a design as relative bounding boxes. |
diagnose(original, reproduction) | Score how faithfully a reproduction matches an original. |
image is an http(s) URL or a base64 data URL.
How it works
Instead of asking a model to regenerate the image (which drifts and never comes back the same), Reprise keeps your original pixels:
- Detect the elements in the design.
- Lift each element out onto its own transparent layer.
- Inpaint the gaps to make a clean background "plate".
- Recompose losslessly — because untouched regions are literally the original pixels, the rebuild is bit-perfect (MAE 0.00, 0 stray pixels), and
diagnosereturns that score so you can check it.
Once it's layered, you can swap copy/colors and mass-produce on-brand variants with the layout fixed.
Honest by design
- Reproduction and unedited layers are bit-perfect (0.00 MAE).
- When you edit a region (swap a subject, change a product), that region is newly generated — not pixel-identical. We measure everything so we never overclaim.
- Auto element-detection is v1 (rembg + OpenCV); it can miss small text. Manual element maps are supported.
- Export today is layered SVG + transparent PNGs (PSD export not yet).
About this repo
This is the public MCP wrapper for Reprise (app.py is the thin server surface). The reproduction engine itself is proprietary and is loaded privately at build time, so it isn't included here. The wrapper is published openly for transparency and so the MCP interface can be relied on.
- Product & early access: https://reprise.design
- Live demo / MCP host: https://tepesama-reprise-mcp.hf.space/
Found an image that breaks it? Open an issue with the image — hardening auto-detection (toward SAM2-class) is the top of the roadmap.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.