mcp-for-blender-pro

Your Blender scene. Your AI models. One creative workspace.

An AI assistant for Blender that can inspect your scene, build objects, edit materials, find assets and carry out multi-step workflows—with a visual chat workspace and a built-in Model Context Protocol (MCP) server.

Download · Getting started · Connections and agents

Turn a creative brief into scene operations

Start with an idea. Ask the assistant to inspect your scene, create a product-display layout, arrange objects, assign materials or prepare an export. Follow its actions in the conversation and inspect the result in the viewport preview. Keep working in Blender throughout the process.

mcp-for-blender-pro brings conversation, scene tools, model choice and agent workflows together. It is designed for artists who want faster iteration, technical artists who automate repetitive work, and developers connecting AI tools to Blender.

Why choose mcp-for-blender-pro?

Capability	What it gives you
Blender-aware assistance	Scene and object inspection gives the assistant context before it acts.
A visual Studio workspace	Chat, scene objects, viewport snapshots, approvals and a task board in a companion window.
Your choice of AI	Connect supported cloud providers, local Ollama models or compatible custom endpoints.
Saved connections	Keep work and personal connections separate, including multiple keys for the same provider.
One assistant or a team	Use a single model for quick changes, or managers, workers and reviewers for structured tasks.
Built-in MCP server	Connect OpenCode and other clients supporting authenticated Streamable HTTP MCP.
21 scene tools	Create, inspect, edit, capture, search assets, consult Blender APIs and export scenes.
Multilingual menus	Choose English, German, French, Spanish or Chinese for the main interface.

From a quick edit to an agent team

Use Single assistant for direct, conversational work. For larger tasks, configure a Team chain with individual responsibilities, instructions and models.

• Manager: breaks the request into assignments and acceptance criteria.
• Workers: perform the assigned scene operations.
• Reviewers: inspect results and approve work or return specific findings.

Tasks run sequentially so scene edits stay ordered. A blocked task gets one correction attempt; a second failed review stops the workflow. The task board exposes assignments, attempts and review findings as work progresses.

Connect the models that fit your work

Supported connections include OpenAI, Anthropic Claude, Google Gemini, OpenRouter, OpenCode Zen, Ollama and custom APIs. Load the available model catalog and select a model directly in Blender or Studio.

Custom endpoints support OpenAI Chat Completions, Anthropic Messages and Ollama protocols. Choose models with tool-calling support; image-capable models can also interpret viewport screenshots. OpenCode-only free models are available through the OpenCode client.

Install and create

---

GitHub에서 전체 내용 보기