vinhelysia GitHub avatar

blender-mcp

vinhelysia

An MCP server that lets AI coding agents control Blender via 26 tools, bridging to the official Blender Lab MCP extension.

Stars

11

7-day growth

No data

Forks

6

Open issues

0

License

MIT

Last updated

2026-07-12

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It is the official connector for Blender Lab's MCP extension, provides an Agent Skill (SKILL.md) for intelligent agent guidance, and supports multiple popular coding platforms (Codex CLI, Grok Build, Cursor, Antigravity, Claude Code) with CLI-variant tools for headless .blend file inspection.

Who it is for

  • AI coding agent users who need to control Blender
  • Blender artists seeking AI-assisted workflows
  • Developers integrating 3D capabilities into LLM-based tools
  • Technical artists automating Blender tasks via natural language

Use cases

  • Create and modify 3D scenes with natural language commands
  • Export selected objects as GLB to disk
  • Inspect .blend file structure headless without opening Blender
  • Take viewport screenshots or render images programmatically

Strengths

  • 26 tools covering both read-only (19) and state-changing (7) operations
  • Built-in Agent Skill (SKILL.md) that teaches agents best practices for reliable scene manipulation
  • Cross-platform setup instructions for Codex CLI, Grok Build, Cursor, Antigravity, and more
  • Multiple agents can share the same Blender instance for non-simultaneous heavy tasks

Considerations

  • Requires Blender 5.1+ and the official Lab MCP extension (not compatible with older community add-ons)
  • Windows Codex desktop app may fail to launch the server due to restricted environment; workaround via uv tool
  • One-shot short-lived connections; concurrent heavy operations from multiple agents are not recommended

README quick start

Usage

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482