What parameters control the size of the 3D model?
You can set `model_width` (default 50.0 mm), `model_thickness` (default 5.0 mm), and `base_thickness` (default 2.0 mm) to define the physical dimensions of the relief.
@Bigchx
Basic information
This project provides a MCP server that converts 2D images into 3D relief models in STL format, suitable for 3D printing or rendering.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp_3d_relief": {
"command": "uv",
"args": [
"--directory",
"{fill_in_your_path_here}",
"run",
"server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Mcp_3d_relief is a Model Context Protocol server that converts 2D images into 3D relief models in STL format. It is designed for makers, designers, and hobbyists who need to generate dimensional reliefs from photographs or graphics for 3D printing, CNC routing, or visualization.
Install the MCP server and configure it with the tool parameters. Invoke the tool by providing an image_path (local file or web URL) along with optional parameters for model dimensions, base thickness, and detail level. The server returns a JSON response containing paths to the generated depth map and STL file. Alternatively, you can use the included Python script directly from the command line: python3 relief.py path/to/your/image.jpg.
You can set `model_width` (default 50.0 mm), `model_thickness` (default 5.0 mm), and `base_thickness` (default 2.0 mm) to define the physical dimensions of the relief.
`detail_level` controls the resolution during processing. At the default of 1.0, the image is processed at 320px, producing STL files typically under 100MB. Higher values improve detail but can increase file size by 4× or more and significantly lengthen processing time.
Yes. Set `skip_depth=false` and provide a depth map generated by an external service (e.g., Depth-Anything-V2). This can produce more accurate 3D reliefs, especially for complex images.
The tool returns a JSON object with `status`, `depth_map_path` (path to the generated depth map PNG), and `stl_path` (path to the STL file). The LLM can access these files using the provided URLs.
Use the Python script directly: `python3 relief.py path/to/your/image.jpg`. Additional parameters can be passed as command-line arguments (see the script's help for details).

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
不止于 CSS
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
Comments