blender-mcp-ultra
Provides MCP tools for controlling Blender, enabling AI agents to create and edit scenes, model meshes, apply PBR materials, build shader and geometry-node setups, light and frame cameras, animate, simulate physics, render, and export assets.
Supports Google as a multi-provider model backend for VLM/visual feedback and render analysis in Blender workflows.
Supports local Ollama models as a multi-provider backend for VLM/visual feedback and render analysis in Blender workflows.
Supports OpenAI as a multi-provider model backend for VLM/visual feedback, allowing agents to analyze renders and iterate on Blender scenes.
Integrates Sketchfab as an asset source so agents can bring Sketchfab 3D assets into Blender scene-building workflows.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
blender-mcp-ultra
The most complete MCP server for Blender — control Blender with natural language from any AI agent: Claude Code, Claude Desktop, Cursor, opencode, Windsurf, Antigravity, LM Studio, Ollama and any Model Context Protocol (MCP) client.
248 tools · Windows / macOS / Linux · headless-ready · production-grade security

Scene above: 100% created and rendered by an AI agent through this MCP server — no manual modeling.
Gallery — what agents build with it
PBR materials | Geometry Nodes | Physics |
|
|
|
|
| rigid body + baked simulation |
Every image above was generated end-to-end through MCP tools — scene setup, materials, lighting, camera framing, simulation and final Cycles render.
Related MCP server: blender-mcp
What is it?
blender-mcp-ultra connects Blender (the free open-source 3D suite) to LLM agents through the Model Context Protocol. Ask your AI assistant to model, texture, light, animate, simulate and render 3D scenes — it executes through 248 typed tools instead of fragile screenshot-guessing.
You: "Create a wooden table with a coffee mug on it and render it in Cycles"
Claude: → object.create, mesh ops, material PBR wood, light.three_point,
camera.set_framing, render.render → escena.pngHighlights
🧰 248 MCP tools (7 base + 241 registry, incl. built-in workflow guidance) — modeling, materials, shader nodes, geometry nodes, lighting, cameras, animation, physics, compositor, UV, rigging, 3D printing, export (FBX/OBJ/glTF/STL), batch, VLM visual feedback, multi-agent collab, scene planner
🖥️ Any MCP client — stdio (Claude Code/Desktop, Cursor, opencode, VS Code, Windsurf), SSE/HTTP (Antigravity, remote), REST
🧠 VLM feedback loop — the agent sees its renders (EEVEE headless capture) and iterates
🔒 Security-first — AST code blocklist validated in gateway and addon, mandatory auth token (auto-generated), localhost-only binding, rate limiting, 0 secrets in history (gitleaks)
🤖 Multi-provider — OpenAI, Anthropic, Google, DeepSeek, Ollama (local)
📦 Asset integrations — PolyHaven, Sketchfab, AmbientCG, Hyper3D
🚀 Headless CI — real E2E tests against Blender in GitHub Actions (Linux + Windows + macOS)
🧪 479 tests passed · ruff · bandit · pip-audit clean
Quick Start
1. Install the Blender addon
Download blender_mcp_ultra.zip → Blender → Edit > Preferences > Add-ons > Install… → enable blender-mcp-ultra → click Connect in the N-panel.
Or install from this repo (Blender 4.2+/5.x):
git clone https://github.com/carlosh7/blender-mcp.git
cd blender-mcp
pip install -e .2. Connect your AI client
Install the gateway (provides the blender-mcp-server command). Startup order doesn't matter: all tools register even if Blender is closed and work as soon as you open it.
pip install blender-mcp-ultraclaude mcp add blender -- blender-mcp-server
# o, desde un checkout del repo:
claude mcp add blender -- python /ruta/a/blender-mcp/mcp_server.pyMore: docs/clients/claude-code.md
{
"mcpServers": {
"blender": {
"command": "blender-mcp-server"
}
}
}More: docs/clients/claude-desktop.md · cursor.md · vscode.md
python mcp_server.py # el addon auto-escribe ~/.config/opencode/mcp.jsonMore: docs/clients/opencode.md
python mcp_server.py --sse # SSE en :9879 (MCP_SSE_HOST para exponer)
# REST local: http://localhost:9877 (mismo token que el socket: ~/.config/blender-mcp/socket_token)
# Docker:
docker build -t blender-mcp-gateway . && docker run -p 9879:9879 blender-mcp-gatewayMore: docs/clients/antigravity.md · docs/remote.md
3. Ask your agent
"Modela una silla de madera con biselado y material PBR, ilumina en 3 puntos y renderiza"Tools (248)
Category | Examples |
Scene |
|
Objects & Mesh |
|
Materials & PBR |
|
Shader / Geo Nodes |
|
Lights & Camera |
|
Animation |
|
Physics | rigid body, cloth, soft body, particles, force fields, constraints, baking |
Render | Cycles/EEVEE settings, |
I/O & Export | FBX, OBJ, glTF, STL + |
UV & Texture | smart UV project, unwrap, bake, textures |
Rigging | armatures, bones, constraints, vertex groups, auto weights |
3D Printing | manifold/watertight checks, scale to mm, dimensions |
Batch & Perf | batch rename/materials/modifiers, turntable, LODs, memory report |
VLM Feedback |
|
Collab & Planner | locks por objeto, mensajes entre agentes, tareas, |
Versioning & Docs |
|
Full reference generated from the live registry: docs_scene tool · skills/recetas en docs/skills/.
Security
Layer | Mechanism |
Transport | localhost-only sockets + shared auth token (auto-generated; |
Code execution | AST blocklist ( |
Input | rate limit (30 req/min) and 1 MB body cap on the HTTP API |
Audit | structured JSON logs with rotation |
Supply chain | gitleaks (full history) + bandit + pip-audit in CI |
Run trusted agents only — executing Blender Python on the agent's behalf is the product.
Architecture
AI Agent (Claude/Cursor/…) ──MCP stdio/SSE──▶ mcp_server.py (gateway, 248 tools)
│ socket :9876 (localhost + token)
▼
Blender + addon blender-mcp-ultra
(handlers, validators, PBR, physics…)mcp_ultra/ # hexagonal: core / adapters / infrastructure / presentation / tools
addon/ # Blender addon: socket server, handlers, PBR factory, anti-blockout
docs/ # client guides, skills recipes, tutorials
tests/ # 479 tests (unit + integration + e2e headless)Testing
pytest tests/unit -q # sin Blender
pytest -q # completo (requiere Blender con el addon conectado)CI ejecuta la suite completa contra Blender headless en cada push (Linux, Windows, macOS).
FAQ
Does it work with ChatGPT / Gemini? Any client that speaks MCP works. For providers without MCP support, the bundled REST API (:9877) accepts plain HTTP.
Does Blender need to be open? Yes for interactive work (it drives the real Blender). CI/headless render jobs run with blender -b — see docs/skills/headless_ci.md.
Is it safe? The agent can execute Blender Python — that's the product. Execution is sandboxed, validated by AST, rate-limited and bound to localhost with token auth. Run trusted agents only.
Blender versions? 4.2+ (LTS) and 5.x. Python 3.10+ for the gateway.
Contributing
PRs welcome — read CONTRIBUTING.md. Docs: GUIDE.md · ARCHITECTURE.md · CHANGELOG.md
License
MIT — see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
Related MCP Servers
- AlicenseCqualityBmaintenanceEnables AI-powered control of Blender through natural language, allowing users to create, manipulate, and automate 3D scenes, objects, materials, animations, and more via Claude or other MCP clients.7165MIT
- AlicenseCqualityDmaintenanceMCP server that enables AI to control Blender 3D, providing 175 typed tools for objects, materials, animation, compositing, and more via the Model Context Protocol.1003MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to inspect and control a live Blender session through MCP tools that create, modify, and delete objects, apply materials, render images, execute Python, and pull PolyHaven assets over a local TCP add-on. It also exposes a provider-agnostic LLM layer that can be pointed at Ollama, LM Studio, llama.cpp, OpenAI-compatible, or Azure endpoints and switched at runtime.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to control a live Blender session — inspecting and editing scenes, objects and materials, rendering images, executing code, and pulling PolyHaven assets — through MCP tools. It also routes prompts to a provider-agnostic LLM backend (Ollama, LM Studio, llama.cpp, OpenAI-compatible, or Azure) that can be switched at runtime.-


