Skip to main content
Glama
BlenderMCP
by ahujasid

Blender MCP

将 Blender 连接到任何 LLM

由 AI 驱动的提示辅助 3D 建模、场景创建与操作。

PyPI Downloads PyPI Version License: MIT Discord

网站 · 完整教程 · Discord · 发布版本 · 赞助

支持者

CodeRabbit Kevin Guanche Darias

所有支持者: 支持本项目


快速开始

三个步骤:安装 uv,将 MCP 服务器指向你的客户端,安装 Blender 插件。

1. 安装 uv

# macOS
brew install uv

# Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

警告: 在安装 uv 之前不要继续。请使用官方安装程序 — 不要使用 pip install uv。

2. 将 MCP 服务器添加到你的客户端

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["blender-mcp"]
        }
    }
}
claude mcp add blender uvx blender-mcp

请参阅下面的 MCP 客户端设置,了解每个客户端的说明和一键安装按钮。

3. 安装 Blender 插件

uvx blender-mcp install-addon

然后在 Blender 中:编辑 → 偏好设置 → 插件 → 启用 界面: Blender MCP。

4. 连接

在 Blender 的 3D 视口中,按 N → 打开 BlenderMCP 选项卡 → 点击 启动 MCP 服务器。就这样 — 让 Claude 帮你构建东西。

注意: 只运行 一个 MCP 服务器实例(要么 Cursor,要么 Claude Desktop),不要同时运行。


Related MCP server: BlenderMCP

目录


功能特性

双向通信

通过基于 socket 的服务器将 Claude AI 连接到 Blender

对象操作

在 Blender 中创建、修改和删除 3D 对象

材质控制

应用和修改材质与颜色

场景检查

获取当前 Blender 场景的详细信息

代码执行

从 Claude 在 Blender 中运行任意 Python 代码

资产与模型生成

通过 Hyper3D Rodin 和 Hunyuan3D 获取 Poly Haven 资产、Sketchfab 模型和 AI 生成的 3D 模型

组件

该系统由两个主要组件组成:

  1. Blender 插件(addon.py)— 一个在 Blender 内创建 socket 服务器以接收和执行命令的 Blender 插件

  2. MCP 服务器(src/blender_mcp/server.py)— 一个实现模型上下文协议并连接到 Blender 插件的 Python 服务器


安装

前提条件

  • Blender 3.0 或更高版本

  • Python 3.10 或更高版本

  • uv 包管理器

macOS

brew install uv

Windows

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

然后在 Windows 中将 uv 添加到用户路径(之后可能需要重启 Claude Desktop):

$localBin = "$env:USERPROFILE\.local\bin"
$userPath = [Environment]::GetEnvironmentVariable("Path", "User")
[Environment]::SetEnvironmentVariable("Path", "$userPath;$localBin", "User")

Linux

curl -LsSf https://astral.sh/uv/install.sh | sh

它会安装到 ~/.local/bin — 打开一个新的 shell 以使其出现在 PATH 中。

否则,安装说明请参阅其网站:安装 uv

在每个操作系统上,请使用 uv 的上述官方安装程序 — 不要使用 pip install uv,后者可能不会创建 uvx 命令,并且可能将 uv 隐藏在客户端无法看到的环境中。

警告: 在安装 uv 之前不要继续。

让客户端找到 uvx

从 GUI 启动的 MCP 客户端(Claude Desktop、Cursor、从 Dock/开始菜单启动的 VS Code)不会继承终端中的 PATH,因此即使 uvx 在你的终端中正常工作,裸的 "command": "uvx" 也可能以 spawn uvx ENOENT 失败。如果发生这种情况:

  • 找到 uvx 的完整路径 — which uvx(macOS/Linux)或 where uvx(Windows)— 并将其用作 "command",例如 /opt/homebrew/bin/uvx 或 C:\Users\<you>\.local\bin\uvx.exe。

  • 在 Windows 上,你也可以用包装方式:"command": "cmd", "args": ["/c", "uvx", "blender-mcp"]。

  • 在更改任何 PATH 或配置后,完全退出并重新启动客户端(Windows:从系统托盘退出,而不仅仅是关闭窗口;macOS:Cmd+Q)。

固定 Python 版本

避免 conda / pyenv / 版本冲突。

uv 会选择哪个 Python 来运行服务器。在安装了 conda(自动激活 base)、pyenv 或 asdf 的机器上 — 或者当有某些依赖项还没有对应 wheel 的较新 CPython 版本时 — uv 可能会选择导致安装失败的解释器。请固定 Python 3.11 并优先使用 uv 管理的解释器,以避免使用 PATH 上的任何解释器:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["--python", "3.11", "blender-mcp"],
            "env": { "UV_PYTHON_PREFERENCE": "only-managed" }
        }
    }
}

--python 3.11 仍然满足此包的 requires-python >=3.10 要求,而 UV_PYTHON_PREFERENCE=only-managed 可防止 uv 首先选择 conda、pyenv、asdf 或系统 Python。(仓库中的 .python-version 只是给贡献者的提示,不会影响 uvx。)

如果修复后之前的失败尝试仍然反复出现,请清除缓存:

uv cache clean blender-mcp && uvx --refresh blender-mcp

不使用 uv 安装

在受限制的机器上,你可以使用 pipx 完全跳过 uvx,然后将客户端指向已安装的命令:

pipx install blender-mcp
pipx ensurepath          # then restart your shell / client

使用生成的绝对路径作为 "command"(用 which blender-mcp / where blender-mcp 找到它)并省略 args。

环境变量

以下环境变量可用于配置 Blender 连接:

变量

默认值

描述

BLENDER_HOST

localhost

Blender socket 服务器的主机地址

BLENDER_PORT

9876

Blender socket 服务器的端口号

示例:

export BLENDER_HOST='host.docker.internal'
export BLENDER_PORT=9876

MCP 客户端设置

Claude for Desktop

观看设置说明视频(假设你已经安装了 uv)

转到 Claude → 设置 → 开发者 → 编辑配置 → claude_desktop_config.json 并包含以下内容:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": [
                "blender-mcp"
            ]
        }
    }
}

使用 Claude Code CLI 添加 blender MCP 服务器:

claude mcp add blender uvx blender-mcp

Cursor

Install MCP Server

macOS — 转到 设置 → MCP 并粘贴以下内容:

  • 要作为全局服务器使用,请使用 "添加新的全局 MCP 服务器" 按钮并粘贴

  • 要作为项目专用服务器使用,请在项目根目录创建 .cursor/mcp.json 并粘贴

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": [
                "blender-mcp"
            ]
        }
    }
}

Windows — 转到 设置 → MCP → 添加服务器,使用以下设置添加新服务器:

{
    "mcpServers": {
        "blender": {
            "command": "cmd",
            "args": [
                "/c",
                "uvx",
                "blender-mcp"
            ]
        }
    }
}

Cursor 设置视频

注意: 只运行 一个 MCP 服务器实例(要么在 Cursor 上,要么在 Claude Desktop 上),不要同时运行。

Visual Studio Code

前提条件:在继续之前,请确保你已安装 Visual Studio Code。

Install in VS Code

OpenCode

{
  "mcp": {
    "blender-mcp": {
      "type": "local",
      "command": ["uvx", "blender-mcp"],
      "enabled": true,
      "environment": {
        "BLENDER_HOST": "localhost",
        "BLENDER_PORT": "9876"
      }
    }
  }
}

Antigravity

{
  "mcpServers": {
    "blender-mcp": {
      "command": "uvx",
      "args": ["blender-mcp"],
      "env": {
        "BLENDER_HOST": "localhost",
        "BLENDER_PORT": "9876"
      }
    }
  }
}

安装 Blender 插件

1. 推荐方式 — 在终端中运行:

uvx blender-mcp install-addon

这会将插件复制到你的 Blender 插件文件夹中,命名为 blender_mcp.py。它会打印写入位置,并保留被替换文件的 .bak 备份。

可选:uvx blender-mcp addon-paths 会列出检测到的 Blender 插件文件夹。使用 BLENDERMCP_ADDONS_DIR=/path/to/scripts/addons 覆盖目标位置。

2. 打开 Blender

3. 转到 编辑 → 偏好设置 → 插件

4. 启用 界面: Blender MCP(搜索 "Blender MCP")。如果尚未出现,请点击 安装… 并选择已复制的 blender_mcp.py / addon.py,或重启 Blender。

5. 手动替代方式 — 如果上述命令找不到你的 Blender 安装,或者你更愿意手动操作:从此仓库下载 addon.py → 在 Blender 中,编辑 → 偏好设置 → 插件 → 安装… → 选择下载的 addon.py → 启用它。

然后在 Blender 的侧边栏中打开 BlenderMCP 选项卡(在 3D 视口中按 N)并点击 启动 MCP 服务器。请参阅下面的 启动连接。

升级(现有用户)

对于新用户,请直接前往 快速开始。对于现有用户,请参阅下文。

1. 通过运行以下命令更新插件文件:

uvx blender-mcp install-addon
uvx blender-mcp addon-paths   # optional: list detected Blender addons folders

2. 在 Blender 中:偏好设置 → 插件 → 禁用并重新启用 界面: Blender MCP(或重启 Blender),然后再次点击 启动 MCP 服务器。

3. 如果服务器包本身需要刷新,请从 Claude 中删除 MCP 服务器并重新添加。

注意: MCP 服务器本身永远不会修改你的 Blender 插件文件。启动时,它会检查已安装的插件是否落后于捆绑副本,并记录如何更新;install-addon 才是实际执行写入的命令,并且它会保留被替换文件的 .bak 备份。轨迹捕获仍然可以通过 execute_code 回退方式在较旧的已加载插件上工作。


使用方法

启动连接

BlenderMCP in the sidebar

  1. 在 Blender 中,转到 3D 视图侧边栏(如果不可见,按 N)

  2. 找到 BlenderMCP 选项卡

  3. 打开你想要使用的复选框(更多信息请参见下面的 功能)

  4. 点击 连接到 Claude

  5. 确保 MCP 服务器在你的终端中运行

与 Claude 一起使用

一旦配置文件已在 Claude 上设置,并且插件在 Blender 中运行,你将看到一个带有 Blender MCP 工具的锤子图标。

侧边栏中的 BlenderMCP

功能

  • 获取场景和对象信息

  • 创建、删除和修改形状

  • 为对象应用或创建材质

  • 在 Blender 中执行任意 Python 代码

  • 通过 Poly Haven 下载合适的模型、资产和 HDRI

  • 从 Sketchfab 搜索并下载模型

  • 通过 Hyper3D Rodin 和 Hunyuan3D 生成 AI 3D 模型

示例命令

以下是一些你可以让 Claude 做的事情示例:

提示

演示

"创建一个地牢中的低多边形场景,有一条龙守护着一罐金子"

观看

"使用 Poly Haven 的 HDRI、纹理和模型(如岩石和植被)创建海滩氛围"

观看

给出一张参考图片,并从中创建 Blender 场景

观看

"获取当前场景的信息,并从中制作一个 threejs 草图"

观看

"通过 Hyper3D 生成一个花园小矮人的 3D 模型"

"把这辆车变成红色和金属质感"

"创建一个球体并将其放在立方体上方"

"让灯光像摄影棚一样"

"将相机对准场景,并使其成为等距视图"


持久化 API 凭据

BlenderMCP 通过 Blender 插件偏好设置支持持久化凭据:

编辑 → 偏好设置 → 插件 → Blender MCP

你可以将这些值存储在那里,以便在 Blender 重启后仍然保留:

  • Sketchfab API 密钥

  • Hyper3D API 密钥

  • Hunyuan3D SecretId / SecretKey

  • Hunyuan3D API URL

对于无头设置或 CI,也可以通过环境变量注入凭据:

变量

BLENDERMCP_SKETCHFAB_API_KEY

BLENDERMCP_HYPER3D_API_KEY

BLENDERMCP_HUNYUAN3D_SECRET_ID

BLENDERMCP_HUNYUAN3D_SECRET_KEY

BLENDERMCP_HUNYUAN3D_API_URL


故障排除

问题

修复

连接问题

确保 Blender 插件服务器正在运行,并且 MCP 服务器已在 Claude 上配置。不要在终端中运行 uvx 命令。有时第一条命令不会通过,但之后就会开始工作。

超时错误

尝试简化你的请求或将其分解为更小的步骤。

Poly Haven 集成

Claude 有时行为不稳定。

你试过关闭再打开吗?

如果仍然遇到连接错误,请尝试重启 Claude 和 Blender 服务器。

技术细节

通信协议

该系统使用基于 TCP 套接字的简单 JSON 协议:

  • 命令 以 JSON 对象形式发送,包含 type 和可选的 params

  • 响应 是包含 status 和 result 或 message 的 JSON 对象

限制与安全注意事项

警告: execute_blender_code 工具允许在 Blender 中运行任意 Python 代码,这可能很强大但潜在危险。在生产环境中请谨慎使用。使用前请务必保存你的工作。

  • Poly Haven 需要下载模型、纹理和 HDRI 图像。如果你不想使用它,请在 Blender 中的复选框中将其关闭。

  • 复杂操作可能需要分解为更小的步骤。

遥测控制

BlenderMCP 收集匿名使用数据以帮助改进工具。遥测同意默认开启,你可以通过两种方式关闭:

1. 在 Blender 中 — 转到 编辑 → 偏好设置 → 插件 → Blender MCP 并取消选中遥测同意复选框。

  • 如果同意(选中,默认):查看 TnC 以了解收集数据的更多详情。

2. 环境变量 — 通过运行以下命令完全禁用所有遥测:

DISABLE_TELEMETRY=true uvx blender-mcp

或将其添加到你的 MCP 配置中:

{
    "mcpServers": {
        "blender": {
            "command": "uvx",
            "args": ["blender-mcp"],
            "env": {
                "DISABLE_TELEMETRY": "true"
            }
        }
    }
}

遥测数据不会与你的姓名或账户关联。它可能用于改进 BlenderMCP、进行研究以及训练 AI 模型。

关于收集内容的完整详情,以及你保持遥测开启所授予的许可,请参阅 TERMS_AND_CONDITIONS.md。


反馈

我们正在积极寻求对 Blender MCP 的反馈。如果你有任何想法,请在此处分享:这里。

如果你有更详细的反馈,可以在此处与我们安排通话:这里 — 我们将在项目中感谢你。

加入社区

提供反馈、获得灵感,并在 MCP 的基础上进行构建:Discord

贡献

欢迎贡献!请随时提交 Pull Request。

免责声明

这是一个第三方集成,并非由 Blender 制作。由 Siddharth 制作。


Star 历史

如果 Blender MCP 对你有用,请考虑给仓库加星

Available Tools

21 tools
download_polyhaven_assetA

Download and import a Polyhaven asset into Blender.

Parameters:

  • asset_id: The ID of the asset to download

  • asset_type: The type of asset (hdris, textures, models)

  • resolution: The resolution to download (e.g., 1k, 2k, 4k)

  • file_format: Optional file format (e.g., hdr, exr for HDRIs; jpg, png for textures; gltf, fbx for models)

Returns a message indicating success or failure.

Inputs: asset_id (required), asset_type (required), resolution, file_format.

download_sketchfab_modelA

Download and import a Sketchfab model by its UID.

Parameters:

  • uid: The unique identifier of the Sketchfab model

Returns a message indicating success or failure. The model must be downloadable and you must have proper access rights.

Inputs: uid (required).

execute_blender_codeB

Execute arbitrary Python code in Blender. Make sure to do it step-by-step by breaking it into smaller chunks.

Parameters:

  • code: The Python code to execute

Inputs: code (required).

generate_hunyuan3d_modelA

Generate 3D asset using Hunyuan3D by providing either text description, image reference, or both for the desired asset, and import the asset into Blender. The 3D asset has built-in materials.

Parameters:

  • text_prompt: (Optional) A short description of the desired model in English/Chinese.

  • input_image_url: (Optional) The local or remote url of the input image. Accepts None if only using text prompt.

Returns:

  • When successful, returns a JSON with job_id (format: "job_xxx") indicating the task is in progress

  • When the job completes, the status will change to "DONE" indicating the model has been imported

  • Returns error message if the operation fails

Inputs: text_prompt, input_image_url.

generate_hyper3d_model_via_imagesA

Generate 3D asset using Hyper3D by giving images of the wanted asset, and import the generated asset into Blender. The 3D asset has built-in materials. The generated model has a normalized size, so re-scaling after generation can be useful.

Parameters:

  • input_image_paths: The absolute paths of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in MAIN_SITE mode.

  • input_image_urls: The URLs of input images. Even if only one image is provided, wrap it into a list. Required if Hyper3D Rodin in FAL_AI mode.

  • bbox_condition: Optional. If given, it has to be a list of ints of length 3. Controls the ratio between [Length, Width, Height] of the model.

Only one of {input_image_paths, input_image_urls} should be given at a time, depending on the Hyper3D Rodin's current mode. Returns a message indicating success or failure.

Inputs: input_image_paths, input_image_urls, bbox_condition.

generate_hyper3d_model_via_textA

Generate 3D asset using Hyper3D by giving description of the desired asset, and import the asset into Blender. The 3D asset has built-in materials. The generated model has a normalized size, so re-scaling after generation can be useful.

Parameters:

  • text_prompt: A short description of the desired model in English.

  • bbox_condition: Optional. If given, it has to be a list of floats of length 3. Controls the ratio between [Length, Width, Height] of the model.

Returns a message indicating success or failure.

Inputs: text_prompt (required), bbox_condition.

get_hunyuan3d_statusA

Check if Hunyuan3D integration is enabled in Blender. Returns a message indicating whether Hunyuan3D features are available.

Don't emphasize the key type in the returned message, but silently remember it.

Inputs: no named parameters.

get_hyper3d_statusA

Check if Hyper3D Rodin integration is enabled in Blender. Returns a message indicating whether Hyper3D Rodin features are available.

Don't emphasize the key type in the returned message, but sliently remember it.

Inputs: no named parameters.

get_object_infoB

Get detailed information about a specific object in the Blender scene.

Parameters:

  • object_name: The name of the object to get information about

Inputs: object_name (required).

get_polyhaven_categoriesA

Get a list of categories for a specific asset type on Polyhaven.

Parameters:

  • asset_type: The type of asset to get categories for (hdris, textures, models, all)

Inputs: asset_type.

get_polyhaven_statusA

Check if PolyHaven integration is enabled in Blender. Returns a message indicating whether PolyHaven features are available.

Inputs: no named parameters.

get_scene_infoB

Get detailed information about the current Blender scene

Inputs: no named parameters.

get_sketchfab_statusA

Check if Sketchfab integration is enabled in Blender. Returns a message indicating whether Sketchfab features are available.

Inputs: no named parameters.

get_viewport_screenshotA

Capture a screenshot of the current Blender 3D viewport.

Parameters:

  • max_size: Maximum size in pixels for the largest dimension (default: 800)

Returns the screenshot as an Image.

Inputs: max_size.

import_generated_assetA

Import the asset generated by Hyper3D Rodin after the generation task is completed.

Parameters:

  • name: The name of the object in scene

  • task_uuid: For Hyper3D Rodin mode MAIN_SITE: The task_uuid given in the generate model step.

  • request_id: For Hyper3D Rodin mode FAL_AI: The request_id given in the generate model step.

Only give one of {task_uuid, request_id} based on the Hyper3D Rodin Mode! Return if the asset has been imported successfully.

Inputs: name (required), task_uuid, request_id.

import_generated_asset_hunyuanA

Import the asset generated by Hunyuan3D after the generation task is completed.

Parameters:

  • name: The name of the object in scene

  • zip_file_url: The zip_file_url given in the generate model step.

Return if the asset has been imported successfully.

Inputs: name (required), zip_file_url (required).

poll_hunyuan_job_statusA

Check if the Hunyuan3D generation task is completed.

For Hunyuan3D: Parameters: - job_id: The job_id given in the generate model step.

Returns the generation task status. The task is done if status is "DONE".
The task is in progress if status is "RUN".
If status is "DONE", returns ResultFile3Ds, which is the generated ZIP model path
When the status is "DONE", the response includes a field named ResultFile3Ds that contains the generated ZIP file path of the 3D model in OBJ format.
This is a polling API, so only proceed if the status are finally determined ("DONE" or some failed state).

Inputs: job_id.

poll_rodin_job_statusA

Check if the Hyper3D Rodin generation task is completed.

For Hyper3D Rodin mode MAIN_SITE: Parameters: - subscription_key: The subscription_key given in the generate model step.

Returns a list of status. The task is done if all status are "Done".
If "Failed" showed up, the generating process failed.
This is a polling API, so only proceed if the status are finally determined ("Done" or "Canceled").

For Hyper3D Rodin mode FAL_AI: Parameters: - request_id: The request_id given in the generate model step.

Returns the generation task status. The task is done if status is "COMPLETED".
The task is in progress if status is "IN_PROGRESS".
If status other than "COMPLETED", "IN_PROGRESS", "IN_QUEUE" showed up, the generating process might be failed.
This is a polling API, so only proceed if the status are finally determined ("COMPLETED" or some failed state).

Inputs: subscription_key, request_id.

search_polyhaven_assetsA

Search for assets on Polyhaven with optional filtering.

Parameters:

  • asset_type: Type of assets to search for (hdris, textures, models, all)

  • categories: Optional comma-separated list of categories to filter by

Returns a list of matching assets with basic information.

Inputs: asset_type, categories.

search_sketchfab_modelsA

Search for models on Sketchfab with optional filtering.

Parameters:

  • query: Text to search for

  • categories: Optional comma-separated list of categories

  • count: Maximum number of results to return (default 20)

  • downloadable: Whether to include only downloadable models (default True)

Returns a formatted list of matching models.

Inputs: query (required), categories, count, downloadable.

set_textureA

Apply a previously downloaded Polyhaven texture to an object.

Parameters:

  • object_name: Name of the object to apply the texture to

  • texture_id: ID of the Polyhaven texture to apply (must be downloaded first)

Returns a message indicating success or failure.

Inputs: object_name (required), texture_id (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 21 tools

    Disambiguation3/5

    The tool set has clear thematic grouping (download, generate, status check, import, poll, search, scene operations), but there is notable overlap within groups. For example, generate_hunyuan3d_model, generate_hyper3d_model_via_images, and generate_hyper3d_model_via_text all generate 3D assets via different methods, which could cause confusion. Similarly, import_generated_asset and import_generated_asset_hunyuan serve similar purposes for different backends. Descriptions help differentiate, but the boundaries are not perfectly distinct.

    Naming Consistency4/5

    Most tools follow a consistent verb_noun pattern (e.g., download_polyhaven_asset, get_scene_info, search_sketchfab_models), with clear and descriptive names. However, there are minor deviations: execute_blender_code uses 'execute' instead of a more specific verb like 'run', and set_texture is a simple verb_noun without a prefix, slightly breaking the pattern. Overall, the naming is highly consistent and predictable.

    Tool Count3/5

    With 21 tools, the count is on the higher side for a Blender integration server, bordering on heavy. While the tools cover multiple functionalities (asset downloading, 3D generation, status checks, scene management), it might feel overwhelming or redundant, such as having separate status and polling tools for each backend. A more streamlined set could improve usability without losing core capabilities.

    Completeness4/5

    The tool surface comprehensively covers the domain of Blender asset management and scene manipulation, including downloading from sources (Polyhaven, Sketchfab), generating 3D assets (Hunyuan3D, Hyper3D), checking statuses, importing assets, polling jobs, searching, and scene info. Minor gaps exist, such as no direct tools for modifying objects or scenes beyond applying textures, but agents can work around this using execute_blender_code. Overall, it supports core workflows effectively.

    Maintenance

    ActivityActive
    ResponsivenessMixed handling

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Connects Blender to Claude AI through the Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, and manipulation through natural language commands.
      17
      2
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Connects Blender to Claude AI through the Model Context Protocol (MCP), enabling prompt-assisted 3D modeling, scene creation, and manipulation.
      17
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Connects Blender to Claude AI through the Model Context Protocol (MCP), enabling prompt-assisted 3D modeling, scene creation, and manipulation directly from Claude.
      17
      MIT