Skip to content
Blender

BlenderMCP Server

by Siddharth Ahuja
Added to Onei
4 views
v1.6.4
MIT
Repository Docs
Featured Developer Tools

Summary

Control Blender from an AI client — build scenes, apply materials, and run Python against the live session.

Features

  • Create and modify 3D scenes through conversation
  • Run Python in Blender for anything not covered by a tool
  • Pull assets from Poly Haven and generate models with Hyper3D

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Blender" tools will be available.
{
  "mcpServers": {
    "blender": {
      "command": "uvx",
      "args": [
        "blender-mcp"
      ]
    }
  }
}

Description

Blender MCP connects an AI assistant to a running Blender session through an add-on, letting it inspect and modify the scene by conversation. It is one of the most visually striking demonstrations of what MCP enables.

What it can do
  • Scene inspection — list objects, read their transforms, materials, and hierarchy
  • Object creation and modification — primitives, transforms, modifiers, and parenting
  • Materials and lighting — create and assign materials, set up lights and world settings
  • Python execution in Blender's interpreter, which is the escape hatch that makes everything else possible: anything the API can do, the assistant can do
  • Asset integration — download models, textures, and HDRIs from Poly Haven, and generate models through Hyper3D Rodin
  • Rendering the current scene and viewing the result
Realistic expectations

It is excellent for scene assembly, procedural work, batch operations, and learning Blender's Python API. It is not going to model a hero character for you. The sweet spot is the tedious middle — arranging, lighting, applying consistent materials, and scripting repetitive edits.

Setup

Install the Blender add-on from the repository, start the connection in Blender, and run uvx blender-mcp in your client.

Related MCP Servers

MCP: Headroom

by Headroom Labs

New

Context-compression MCP server that shrinks tool outputs, logs, files and RAG chunks before they reach the model, cutting 60-95% of tokens on JSON payloads.

Developer Tools
3 views

MCP: Engram

by Gentleman Programming

New

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

Developer Tools
2 views

MCP: agent-device

by Callstack

New

Give a coding agent a live feedback loop on real mobile, TV and desktop apps — inspect, tap, type and capture evidence on iOS, Android and HarmonyOS over MCP or a CLI.

Developer Tools
3 views
Browse all MCP servers →