# Threedee (Meshy)

> Use this tool when you need to generate 3D models from text descriptions or images, and want to refine them with PBR textures or convert images to 3D objects. It solves problems of creating 3D assets without specialized modeling skills, providing a conversational interface for users to input text or images and output customized 3D models. Ideal for use cases where AI-driven 3D content creation is required, such as architecture, product design, or gaming, with inputs including text descriptions or images and outputs being refined 3D models.

Canonical page: https://skillsregistry.net/skills/fabianh001-threedee-meshy  
JSON: https://api.skillsregistry.net/v1/skills/fabianh001-threedee-meshy

## Description

ThreeDee-MCP is a server implementation that enables AI assistants to generate 3D models from text descriptions or images through the Meshy API. Built with Python and FastMCP, it provides tools for creating 3D previews, refining models with PBR textures, converting images to 3D objects, and managing tasks with detailed status tracking. The implementation includes a JavaScript backend using Bun and Anthropic's Claude for natural language processing, making it particularly valuable for users who want to create 3D assets through conversational interfaces without specialized modeling skills. Developed as a hackathon project for Paris AI Tinkerers, it demonstrates practical integration of generative AI with 3D content creation workflows.

## Trust

- **Trust score (0–1):** 0.84
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/fabianh001-threedee-meshy)
- **Repository:** <https://github.com/fabianh001/threedee-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "fabianh001-threedee-meshy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fabianh001-threedee-meshy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fabianh001-threedee-meshy/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt