A
licenseNot graded
qualityD
maintenanceEnables interactive selection of image regions from images and PDFs, with OCR support and automated export of selected regions as separate files.
MIT
relief-mcp
by noon0ri
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., "@relief-mcpMake a relief of the dog and the person in ~/Pictures/dog.jpg"
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.
relief-mcp
An MCP server that turns parts of a photo into a layered 3D relief — like a museum bas-relief — that tilts
with the pointer. Claude looks at the photo, picks the parts with boxes, you approve the overlay it shows
you, and the server writes one GLB per part plus relief.html, a single self-contained file you can open in
any browser — no server needed, no dependencies to install to view it.
Install
With Claude Code:
claude mcp add relief -- npx -y @noon0ri/relief-mcpFrom source
git clone https://github.com/noon0ri/relief-mcp.git
claude mcp add relief -s user -- node /path/to/relief-mcp/mcp/server.mjsThen ask, for example: "Make a relief of the dog and the person in ~/Pictures/dog.jpg".
Related MCP server: Stable Fast 3D MCP Server
What you need
Node 20.9 or newer.
The first call downloads the segmentation and depth models, about 89 MB, cached at
~/.cache/relief-mcp(override withRELIEF_MCP_CACHE). Later calls use the cache.Installing the package pulls in about 530 MB of dependencies (
onnxruntime-nodeandsharpare most of it). The server uses about 1.4 GB of memory while it runs.
How it works / tools
Tool | What it does |
| Loads the photo, returns it with a coordinate grid and its working size (long side at most 1024 px). |
| Selects parts, front-most first. Each part is |
| Writes |
The intended loop: segment_parts shows you an overlay (each part tinted and numbered) and Claude describes
what it picked; only after you say it looks right does Claude call make_relief, and you get one more chance
to confirm in the dialog before files are written.
Privacy
Your photo never leaves your computer. The only thing downloaded over the network is the model files, from
Hugging Face, once, and cached locally. Results are written next to the photo, in <photo folder>/<photo name>-relief/. The overlay image and a small log of confirmation-dialog answers are written to a temp
folder (elicit.log and the overlay JPEG) so you can review them later.
Tested / not tested
Checked on macOS (arm64) with Claude Code 2.1.278. Claude Desktop, Windows and Linux have not been run.
relief.html was checked in Chrome (headless) and confirmed to open correctly in Safari; other browsers are
untested.
License
MIT. The two models it downloads at runtime are each licensed separately and are not redistributed by this
package: facebook/sam2.1-hiera-tiny and
depth-anything/Depth-Anything-V2-Small-hf,
both Apache-2.0.
This server cannot be deployed
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Turn text and images into 3D models for games, rendering and 3D printing.
Turn text or an image into an animation-ready 3D model (GLB): generate, rig, animate, retexture.
Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment.
Generate 3D models from images or text with AI, then retexture or convert them to STL, 3MF or OBJ.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables generating 3D models (GLB files) from 2D images using Stability AI's Stable Fast 3D API, with customizable parameters and credit balance checking.MIT
- AlicenseNot gradedqualityDmaintenanceReconstructs a reference image as procedural 3D geometry through a staged pipeline, generating a Three.js model, preview, comparison, and glTF export.MIT
- AlicenseAqualityCmaintenanceEnables local image-driven displacement of STL/OBJ meshes, STL/3MF export, and agent-driven texturing workflows without remote services.3AGPL 3.0