Open Models MCP for Blender Using Ollama

What is dhakalnirajan blender open mcp

blender-open-mcp

blender-open-mcp is an open source project that integrates Blender with local AI models (via Ollama) using the Model Context Protocol (MCP). This allows you to control Blender using natural language prompts, leveraging the power of AI to assist with 3D modeling tasks.

Features

  • Control Blender with Natural Language: Send prompts to a locally running Ollama model to perform actions in Blender.
  • MCP Integration: Uses the Model Context Protocol for structured communication between the AI model and Blender.
  • Ollama Support: Designed to work with Ollama for easy local model management.
  • Blender Add-on: Includes a Blender add-on to provide a user interface and handle communication with the server.
  • PolyHaven Integration (Optional): Download and use assets (HDRIs, textures, models) from PolyHaven directly within Blender via AI prompts.
  • Basic 3D Operations:
    • Get Scene and Object Info
    • Create Primitives
    • Modify and delete objects
    • Apply materials
  • Render Support: Render images using the tool and retrieve information based on the output.

Installation

Prerequisites

  1. Blender: Blender 3.0 or later. Download from blender.org.
  2. Ollama: Install from ollama.com, following OS-specific instructions.
  3. Python: Python 3.10 or later.
  4. uv: Install using pip install uv.
  5. Git: Required for cloning the repository.

Installation Steps

  1. Clone the Repository:

    git clone https://github.com/dhakalnirajan/blender-open-mcp.git
    cd blender-open-mcp
    
  2. Create and Activate a Virtual Environment (Recommended):

    uv venv
    source .venv`/bin/activate`  # On Linux/macOS
    .venv\Scripts\activate  # On Windows
    
  3. Install Dependencies:

    uv pip install -e .
    
  4. Install the Blender Add-on:

    • Open Blender.
    • Go to Edit -> Preferences -> Add-ons.
    • Click Install....
    • Select the addon.py file from the blender-open-mcp directory.
    • Enable the "Blender MCP" add-on.
  5. Download an Ollama Model (if not already installed):

    ollama run llama3.2
    

    (Other models like Gemma3 can also be used.)

Setup

  1. Start the Ollama Server: Ensure Ollama is running in the background.

  2. Start the MCP Server:

    blender-mcp
    

    Or,

    python src/blender_open_mcp/server.py
    

    By default, it listens on http://0.0.0.0:8000, but you can modify settings:

    blender-mcp --host 127.0.0.1 --port 8001 --ollama-url http://localhost:11434 --ollama-model llama3.2
    
  3. Start the Blender Add-on Server:

    • Open Blender and the 3D Viewport.
    • Press N to open the sidebar.
    • Find the "Blender MCP" panel.
    • Click "Start MCP Server".

Usage

Interact with blender-open-mcp using the mcp command-line tool:

Example Commands

  • Basic Prompt:

    mcp prompt "Hello BlenderMCP!" --host http://localhost:8000
    
  • Get Scene Information:

    mcp tool get_scene_info --host http://localhost:8000
    
  • Create a Cube:

    mcp prompt "Create a cube named 'my_cube'." --host http://localhost:8000
    
  • Render an Image:

    mcp prompt "Render the image." --host http://localhost:8000
    
  • Using PolyHaven (if enabled):

    mcp prompt "Download a texture from PolyHaven." --host http://localhost:8000
    

Available Tools

Tool Name Description Parameters
get_scene_info Retrieves scene details. None
get_object_info Retrieves information about an object. object_name (str)
create_object Creates a 3D object. type, name, location, rotation, scale
modify_object Modifies an object’s properties. name, location, rotation, scale, visible
delete_object Deletes an object. name (str)
set_material Assigns a material to an object. object_name, material_name, color
render_image Renders an image. file_path (str)
execute_blender_code Executes Python code in Blender. code (str)
get_polyhaven_categories Lists PolyHaven asset categories. asset_type (str)
search_polyhaven_assets Searches PolyHaven assets. asset_type, categories
download_polyhaven_asset Downloads a PolyHaven asset. asset_id, asset_type, resolution, file_format
set_texture Applies a downloaded texture. object_name, texture_id
set_ollama_model Sets the Ollama model. model_name (str)
set_ollama_url Sets the Ollama server URL. url (str)
get_ollama_models Lists available Ollama models. None

Troubleshooting

If you encounter issues:

  • Ensure Ollama and the blender-open-mcp server are running.
  • Check Blender’s add-on settings.
  • Verify command-line arguments.
  • Refer to logs for error details.

For further assistance, visit the GitHub Issues page.


Happy Blending with AI! 🚀

Leave a Comment

Frequently Asked Questions

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.

What are MCP Servers?

MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.

How do MCP Servers work?

MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.

Are MCP Servers secure?

Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.

Related MCP Servers

chrisdoc hevy mcp avatar

chrisdoc hevy mcp

mcp
sylphlab pdf reader mcp avatar

sylphlab pdf reader mcp

An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.

pdf-parsetypescriptnodejs
aashari mcp server atlassian bitbucket avatar

aashari mcp server atlassian bitbucket

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.

atlassianrepositorymcp
aashari mcp server atlassian confluence avatar

aashari mcp server atlassian confluence

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.

atlassianmcpconfluence
prisma prisma avatar

prisma prisma

Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB

cockroachdbgomcp
Zzzccs123 mcp sentry avatar

Zzzccs123 mcp sentry

mcp sentry for typescript sdk

mcptypescript
zhuzhoulin dify mcp server avatar

zhuzhoulin dify mcp server

mcp
zhongmingyuan mcp my mac avatar

zhongmingyuan mcp my mac

mcp
zhixiaoqiang desktop image manager mcp avatar

zhixiaoqiang desktop image manager mcp

MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)

mcp
zhixiaoqiang antd components mcp avatar

zhixiaoqiang antd components mcp

An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询

designantdapi

Submit Your MCP Server

Share your MCP server with the community

Submit Now