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., "@img2threejs-mcp reconstruct a 3D model from the image of a chair"
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.
A bounded MCP pipeline for reconstructing a reference image as procedural 3D geometry.
It adapts the staged workflow of hoainho/img2threejs, but deliberately exposes no
shell, caller paths, downloads, arbitrary TypeScript, or unrestricted code execution.
reference → asset transaction → locked build pass → preview/comparison → visual review → GLB export
Each accepted scene specification generates:
normalized spec.json
editable createModel.ts Three.js factory
deterministic preview.png
side-by-side comparison.png
Unity-compatible glTF 2.0 asset.glb
SHA-256 manifest and immutable export package
Related MCP server: trident-mcp
Call img2threejs_policy, create an asset, validate each pass before building it, inspect
the comparison image, review the pass, and export only after validation.
The service listens only on 127.0.0.1:10851/mcp.
.venv\Scripts\python.exe -m unittest discover -s tests -v
.venv\Scripts\python.exe scripts\smoke_test.pySee docs/SCENE_SPEC.md and THIRD_PARTY_NOTICES.md.
This server cannot be deployed
Turn text or an image into an animation-ready 3D model (GLB): generate, rig, animate, retexture.
3D avatar/asset foundry: text/image -> rigged, validated, engine-ready GLB via x402.
Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment.
Generate, edit, and deploy immersive 3D/WebGL web projects from any MCP assistant.
