Blender Ai Mcp

Created By

PatrykIti22 days ago

Modular MCP Server + Blender Addon for AI-Driven 3D Modeling. Enable LLMs (Claude, ChatGPT) to control Blender reliably. Built with Clean Architecture for stability and scalability.

# blender

# mcp

Overview Content Tools Comments

Content

🚀 Why use this MCP Server instead of raw Python code?

Most AI solutions for Blender rely on asking the LLM to "write a Python script". This often fails because:

Hallucinations: AI frequently uses outdated bpy API methods (mixing Blender 2.8 with 4.0).
Context Errors: Running operators requires specific context (active window, selected object, correct mode). Raw scripts often crash Blender due to poll() failures.
No Feedback Loop: If a script fails, the AI doesn't know why. Our MCP server returns precise error messages.
Safety: Executing arbitrary Python code is risky. Our tools are sandboxed endpoints with validated inputs.

Blender AI MCP acts as a stable Translation Layer, handling the complexity of Blender's internal state machine so the AI can focus on creativity.

🗺️ Roadmap & Capabilities

Our goal is to enable AI to model complex 3D assets—from organs and biological structures to hard-surface precision parts (cars, devices).

✅ Phase 1: Object & Scene Management (Completed)

Basic composition and scene understanding.

[x] Scene: List, Delete, Duplicate, Set Active, Clean Scene.
[x] Vision: get_viewport (AI sees the scene).
[x] Construction: Create Lights, Cameras, Empties.
[x] Object Ops: Create Primitives, Transform (Move/Rotate/Scale), Set Origin.
[x] Modifiers: Add Modifier, Apply Modifier, List Modifiers.
[x] Structure: Join Objects, Separate Objects, Convert to Mesh.

🚧 Phase 2: Mesh Editing (Edit Mode) - Next Up

Critical for shaping geometry. AI needs these to actually "model" details, not just move cubes around.

[ ] mesh_extrude (The basis of modeling).
[ ] mesh_loop_cut (Adding topology).
[ ] mesh_bevel (Rounding edges).
[ ] mesh_inset (Creating panels/windows).
[ ] mesh_boolean (Destructive cutting).
[ ] mesh_merge_by_distance (Cleaning topology).
[ ] mesh_smooth / mesh_flatten.

⏳ Phase 3: Materials & Organization

[ ] material_create: Setup PBR materials.
[ ] material_assign: Assign to objects/faces.
[ ] uv_unwrap: Smart UV Project / Cube Projection.
[ ] collection_manage: Organize hierarchy.
[ ] export: Save to GLB/FBX/OBJ.

⭐ Phase 4: Macro Tools (The "Magic" Layer)

High-level abstractions where one command executes hundreds of Blender operations.

[ ] macro_organify: Converts blockouts to organic shapes (hearts, lungs).
[ ] macro_create_phone_base: Generates smartphone chassis with accurate topology.
[ ] macro_human_blockout: Generates proportional human base meshes.
[ ] macro_retopologize: Automates low-poly conversion.

Server Config

{
  "mcpServers": {
    "blender-ai-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "BLENDER_RPC_HOST=host.docker.internal",
        "ghcr.io/patrykiti/blender-ai-mcp:latest"
      ],
      "disabled": false,
      "autoApprove": [
        "scene_list_objects",
        "scene_delete_object",
        "scene_clean_scene",
        "scene_duplicate_object",
        "scene_set_active_object",
        "scene_get_viewport",
        "scene_create_light",
        "scene_create_camera",
        "scene_create_empty",
        "modeling_create_primitive",
        "modeling_transform_object",
        "modeling_add_modifier",
        "modeling_apply_modifier",
        "modeling_convert_to_mesh",
        "modeling_join_objects",
        "modeling_separate_object",
        "modeling_set_origin",
        "modeling_list_modifiers"
      ]
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Amap Maps高德地图官方 MCP Server

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Serper MCP ServerA Serper MCP Server

ChatWiseThe second fastest AI chatbot™

Playwright McpPlaywright MCP server

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

CursorThe AI Code Editor

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs