blender-ai-mcp-addon is a free, open source ai interaction & interfaces project written in several languages and released under MIT. It has 1,599 GitHub stars, 38 forks and 70 open issues, and was last pushed 4 days ago. On this registry it ranks #123 of 165 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available.

What is blender-ai-mcp-addon?

blender-ai-mcp-addon is an MIT-licensed Blender add-on, distributed as mcp-for-blender-pro, that gives artists, technical artists and developers a visual AI chat workspace, 21 scene tools and a built-in Model Context Protocol server inside Blender, working with cloud providers or local Ollama models.

What it is

blender-ai-mcp-addon is an add-on for Blender 4.2 and later, published under the product name mcp-for-blender-pro, that combines a visual AI chat workspace, a set of scene tools and a built-in Model Context Protocol server inside Blender. It lives in the Blender add-on ecosystem and connects to external model providers rather than shipping its own: OpenAI, Anthropic Claude, Google Gemini, OpenRouter, OpenCode Zen, Ollama and custom endpoints speaking the OpenAI Chat Completions, Anthropic Messages or Ollama protocols.

The concrete problem it addresses is the gap between a creative brief and the bpy Python scripting needed to carry it out. Instead of hand-writing scripts to inspect, create, arrange, material-assign or export, a user states the task in chat, and the assistant first gathers scene and object context before acting through the scene tools. The README frames the audience as artists who want faster iteration, technical artists who automate repetitive work, and developers connecting AI tools to Blender.

Key capabilities

  • A visual Studio companion window that brings chat, scene objects, viewport snapshots, approvals and a task board together alongside the Blender viewport.
  • 21 scene tools that create, inspect, edit, capture, search assets, consult Blender APIs and export scenes.
  • Connections to OpenAI, Anthropic Claude, Google Gemini, OpenRouter, OpenCode Zen, Ollama and custom APIs, including custom endpoints that speak OpenAI Chat Completions, Anthropic Messages or Ollama protocols, with saved connections that keep work and personal credentials separate and allow multiple keys for the same provider.
  • A Single assistant mode for direct conversational work and a Team chain mode with manager, worker and reviewer roles, run sequentially so scene edits stay ordered.
  • A review guard in the Team chain: a blocked task gets one correction attempt, a second failed review stops the workflow, and the task board exposes assignments, attempts and review findings as work progresses.
  • A built-in MCP server using authenticated Streamable HTTP MCP, so OpenCode and other compatible clients can connect.
  • Menus in English, German, French, Spanish and Chinese for the main interface.

Who uses it and how

  • Artists seeking faster iteration can start from a brief and ask the assistant to inspect the scene, create a product-display layout, arrange objects, assign materials or prepare an export, following the actions in the conversation and viewport preview while continuing to work in Blender.
  • Technical artists use the scene tools to automate repetitive work that would otherwise require hand-written bpy scripting.
  • Developers connect AI tools to Blender through the authenticated Streamable HTTP MCP server, for example from an OpenCode client, where OpenCode-only free models are available.
  • Individuals and small teams keep work and personal provider connections separate, and move from a single assistant for quick changes to a manager-worker-reviewer chain for larger structured tasks.

Getting started

Download mcp-for-blender-pro.zip from the Releases page, then in Blender open Edit → Preferences → Get Extensions → menu → Install from Disk, select the ZIP and enable mcp-for-blender-pro; the add-on appears under 3D Viewport → N → MCP Pro, where a provider, connection details and model are chosen. The published release bundle targets Windows x64 with Blender 4.2 or later.

How it compares

The facts for this entry list no paid products that the add-on replaces and name no similar tools for comparison. Within this registry it stands alone as the described Blender add-on that pairs a visual AI workspace with a built-in MCP server.

When to use it — and when not to

Choose it when work happens in Blender 4.2 or later on Windows x64 and scene-aware chat inside the viewport is preferable to writing bpy scripts, especially where provider credentials or a local Ollama endpoint are already available. A self-hoster must supply that model access and manage the provider connections, because the add-on connects to external services rather than bundling model access. It is a poor fit for anyone wanting a zero-configuration hosted service or a documented install path outside the Windows x64 bundle, and the repository's 70 open issues are worth reviewing before adoption.

project readme (upstream, from github) — read inline

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.

Blender 4.2+ Release 1.0.0 Windows x64 MIT

Download · Getting started · Connections and agents

AI chat workspace with a live Blender scene preview

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.

Agent roles and model configuration

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.

Provider, saved connection and model selection

Install and create

  1. Download mcp-for-blender-pro.zip from Releases.
  2. In Blender, open Edit → Preferences → Get Extensions → menu → Install from Disk.
  3. Select the ZIP, enable mcp-for-blender-pro, then open 3D Viewport → N → MCP Pro.
  4. Choose a provider, add your connection details and select a model.
  5. Send a message in Blender or click Open Studio Window.

The release bundle targets Windows x64 with Blender 4.2 or later. Keep Blender open while using Studio or an external client.

Try these prompts

Inspect this scene and explain its object structure before making any changes.

Create a simple product-display scene with a pedestal, a camera and three lights. Give the pedestal a matte blue material.

Duplicate the selected object into a neatly spaced row of five and show the viewport.

Find an appropriate Poly Haven asset for this scene and ask before importing it.

Blender automation through MCP

Launch OpenCode Portable from the sidebar to work through OpenCode with the Blender connection configured for you. OpenCode manages its own provider sign-in and model selection. Other compatible MCP clients can connect to the authenticated local endpoint described in the connection guide.

Tool group Included tools
Scene inspection get_scene_info, list_objects, get_object_info
Object creation add_cube, add_sphere, add_cylinder, add_plane, add_light, add_camera
Editing move_object, duplicate_object, delete_object, parent_objects, set_material
Visual feedback and scripting viewport_screenshot, execute_code
Blender API and export bpy_api_lookup, describe_node_type, export_scene
Asset workflows search_assets, import_asset

Asset integrations include Poly Haven, Sketchfab and Poly Pizza. Configure service keys where required and follow the licenses of the assets you use.

Stay in control of your scene

Built-in chat supports operation approvals, cancellation after the current step and named undo steps for mutations. Python tool validation helps catch disallowed operations; it is not a security sandbox. External MCP clients manage their own approval policies.

Connection credentials are stored in your user settings. Chat history lasts for the current session. Studio runs locally and authenticates requests to Blender.

Keywords

mcp-for-blender · blender mcp server · blender mcp · blender ai · ai for blender · blender ai assistant · blender chatgpt · blender claude · blender openai · blender gemini · blender llm · blender ollama · blender agents · blender multi-agent · blender copilot · ai blender addon · blender extension · blender addon · blender plugin · blender automation · blender scripting · blender python · bpy api · blender api · geometry nodes · 3d modeling · 3d automation · 3d workflow · scene generation · ai modeling · ai materials · ai textures · viewport screenshot · model context protocol · mcp integration · opencode blender · ai tools for blender · blender workflow · chat in blender · ai chat blender

License

Released under the MIT license. OpenCode's license is included with the distribution. Independent project; not affiliated with or endorsed by the Blender Foundation or the listed AI providers.

Frequently asked questions

Is blender-ai-mcp-addon free to use?

blender-ai-mcp-addon is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does blender-ai-mcp-addon do?

AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT, Claude, Gemini, Ollama, OpenCode. Blender AI a

What is blender-ai-mcp-addon written in?

blender-ai-mcp-addon's source is publicly available at https://github.com/hitkeeen/blender-ai-mcp-addon, with 1,599 GitHub stars.