Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Reprise Reproduce the design from https://example.com/design.png"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
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/httpEndpoints: /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.
Related MCP server: mcp-design-platform
Tool | What it does |
| Un-flatten a flat design into editable layers and reproduce it bit-perfect. Returns a fidelity score (MAE / PSNR / exact-match % / stray px). |
| Detect the elements (subjects and text) in a design as relative bounding boxes. |
| Score how faithfully a reproduction matches an original. |
image is an http(s) URL or a base64 data URL.
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 diagnose returns 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.
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).
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.
This server cannot be deployed
Un-flatten any flat AI design into editable layers, reproduce it bit-perfect, from your agent.
Agent-Native design tool - create and edit visual designs with agent assistance
Brand-safe MCP for AI agents to create editable, on-brand graphics and automate variants.
Give your AI agents a design superpower. Generate, edit, and publish publication-grade decks, reports, landing pages, resumes, and marketing visuals directly within your agent workflow. Delivering frontier-level design quality at 3× the speed and 53× lower cost -from conversational prompt to live link or vector PDF in minutes.
