Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Blender To Antigravity

БесплатноНе проверен

Connect Blender 5.1+ to Antigravity via Model Context Protocol (MCP) for natural language scene querying, geometry node auto-documentation, and automated 3D wor

GitHubEmbed

Описание

Connect Blender 5.1+ to Antigravity via Model Context Protocol (MCP) for natural language scene querying, geometry node auto-documentation, and automated 3D workflow execution.

README

Connect Blender 5.1+ to Antigravity via the Model Context Protocol (MCP). Execute scene queries, automated scene cleanup, and geometry node documentation using natural language.

Antigravity (LLM Client) └─► blender-mcp (MCP Server via Stdio) └─► Companion Add-on (Local Bridge) └─► Active Blender Session (Python API)

Security Advisory: The MCP server executes Python code directly inside Blender without sandbox restrictions. Only run sessions on trusted files or in a dedicated test environment, and ensure production assets are backed up before executing automated workflows.


Overview

Four components work together to bridge your AI client with Blender:

  1. Active Blender Session: Runs your project scene (Blender 5.1+ recommended).
  2. Blender Companion Add-on: Exposes a local communication bridge inside Blender.
  3. MCP Server (blender-mcp): Connects Antigravity to Blender via standard input/output (Stdio).
  4. LLM Client (Antigravity): Sends natural language requests and executes actions via tools.

Prerequisites

Before setting up the connection, ensure you have installed:

  • Blender 5.1 or newer: Download from blender.org.
  • uv / uvx (Python tool runner):
    • macOS: brew install uv
    • Linux / macOS (curl): curl -LsSf https://astral.sh/uv/install.sh | sh
    • Windows (PowerShell): powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Installation & Configuration

Step 1: Install the Blender Companion Add-on

Install the add-on using any of the following methods:

  • Method 1: Drag & Drop (Recommended) Open Blender, then drag the install button from blender.org/lab/mcp-server into Blender twice (the first drop adds the repository, the second installs the add-on and enables update alerts).
  • Method 2: Install from Disk Download the latest release zip from the Blender MCP releases page. In Blender, go to Preferences > Get Extensions, open the top-right menu, and select Install from Disk...
  • Method 3: Command-Line Installer Run uvx blender-mcp install-addon in your terminal, then enable Blender MCP under Blender Preferences.

Important: Keep Blender open and running in the background with the add-on enabled whenever interacting with your AI agent.


Step 2: Configure Your Agent Client

Add the blender MCP server definition to your MCP configuration file:

  • Global Path: ~/.gemini/config/mcp_config.json
  • Project Path: .agents/mcp_config.json
{
  "mcpServers": {
    "blender": {
      "command": "uvx",
      "args": [
        "blender-mcp"
      ]
    }
  }
}

Step 3: Verification

Start Blender with any scene open.

Open a new chat in Antigravity.

Send the prompt: "Check Blender MCP status and summarize the active scene."

The agent will verify the add-on handshake and return the scene details.

Powerful Workflows

Name Prompt What it does
Find Heavy Outliers "Analyze the scene and list the outliers: objects with highest polygon count but smaller size from the camera point of view." Finds background meshes with excessive subdivision levels that can be optimized or replaced with normal maps.
Automated Data-Block Cleanup "With the current open Blender file, fix the names of all data-blocks to remove typos and follow standard conventions." Renames lights, meshes, materials, and textures systematically (e.g., Camera → CAM-main, LGT-Lights → LGT-lights).
Relational Scene Queries "Which objects in this file are using the pebble material?" Traverses the full dependency graph and material slots via natural language.
Geometry Nodes Auto-Doc "Explain what the main geometry nodes setup is doing. Add inline documentation with frame elements and create a Text data-block." Analyzes the node graph, places organized color-coded layout frames, and writes full documentation into Blender's text editor.

Quick Troubleshooting

  • Add-on Version Mismatch: Re-run uvx blender-mcp install-addon or update via Blender's extension manager, then restart the add-on.

  • Connection Failed: Ensure Blender is actively running and the companion add-on is toggled on in Blender Preferences.

  • uvx Not Found: Confirm your terminal or editor has ~/.cargo/bin or ~/.local/bin included in its $PATH.

from github.com/JohanScheepers/Blender-to-Antigravity

Установка Blender To Antigravity

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/JohanScheepers/Blender-to-Antigravity

FAQ

Blender To Antigravity MCP бесплатный?

Да, Blender To Antigravity MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Blender To Antigravity?

Нет, Blender To Antigravity работает без API-ключей и переменных окружения.

Blender To Antigravity — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Blender To Antigravity в Claude Desktop, Claude Code или Cursor?

Открой Blender To Antigravity на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Opencode Omniroute Plugin

OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc

GitHub Actionsавтор: GitHub Actions
85

Roblox Studio

Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce

paralovавтор: paralov

Antigravity Drawio

MCP server that enables AI assistants to create, parse, render, and validate Draw.io diagrams programmatically.

S-SUJAN-Sавтор: S-SUJAN-S

Fetch

Web content fetching and conversion for efficient LLM usage.

автор: Community

AWS KB Retrieval

Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.

modelcontextprotocolавтор: modelcontextprotocol

Spring AI MCP Server

Provides auto-configuration for setting up an MCP server in Spring Boot applications.

автор: Community

llm-analysis-assistant

A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also

xuzexin-hzавтор: xuzexin-hz

MCP-Agent

A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)

lastmile-aiавтор: lastmile-ai

Spring AI MCP Client

Provides auto-configuration for MCP client functionality in Spring Boot applications.

автор: Community

mcp.natoma.ai

A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)

автор: Community

Compare Blender To Antigravity with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai