Text-to-3D in Blender: MCP Bridge Lets One Prompt Build a 3D Taj Mahal at Sunset
sidahuj · x · 2026-09-21
A demo shows issuing a single natural-language command — "Astra, make a 3D model of the Taj Mahal at sunset using MCP for Blender" — and having an AI agent build the scene directly inside Blender via the Model Context Protocol. It's a neat showcase of wiring LLMs into professional 3D tools through MCP, pointing toward conversational 3D content creation workflows without manual modeling.
Related event: Blender MCP project goes viral, generating 3D models from a single prompt(2 posts)→
More from coding & agent
- Rethinking classifiers: conversation+tool templates as special cases of inference-time specs — austinvhuang · 2026-09-21
- Analyst predicts Meta will pay Amazon for agent access, spawning a new agent business model — signulll · 2026-09-21
- Arena: coding-agent harnesses show up to 5x cost differences at similar success rates — thione · 2026-09-21
- Recap: Anthropic merged Claude chat and Cowork, redesigned Claude Code Projects — thione · 2026-09-21
- Recap repeat: Claude Code Projects parallel cloud sessions and Astra for Law — thione · 2026-09-21
- Recap: WorkOS explains agent auth with auth.md; Salesforce and Anthropic expand Claudeforce — thione · 2026-09-21