dcc-mcp-blender
Allows MCP clients to control Blender for 3D scene management, object manipulation, materials, rendering, geometry nodes, physics, and scripting via 55+ built-in tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dcc-mcp-blendercreate a cube and change its color to blue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dcc-mcp-blender
Blender addon for the DCC Model Context Protocol (MCP) ecosystem — embeds a Streamable HTTP MCP server directly inside Blender, letting any MCP-compatible AI client drive your 3D workflow.
Overview
dcc-mcp-blender turns Blender into a first-class MCP server. Once the addon is enabled, any MCP client (Claude Desktop, custom agents, etc.) can call Blender tools over HTTP without any external gateway.
┌─────────────────────────────────┐
│ Blender (Python 3.10+) │
├─────────────────────────────────┤
│ dcc_mcp_blender │
│ ├─ BlenderMcpServer │
│ ├─ SkillCatalog (150+ tools) │
│ ├─ ActionRegistry │
│ └─ HTTP Handlers │
├─────────────────────────────────┤
│ dcc-mcp-core │
│ ├─ McpHttpServer │
│ ├─ JSON-RPC 2.0 │
│ └─ SSE Streaming │
└─────────────────────────────────┘
↓ http://127.0.0.1:8765/mcp
┌─────────────────────────────────┐
│ MCP Host (Claude / etc.) │
└─────────────────────────────────┘Features
Embedded MCP server — no external gateway needed; the server runs inside Blender's Python interpreter
150+ pre-built tools — scene management, object manipulation, mesh/UV editing, rigging, pose libraries, interchange, materials, node graphs, rendering, physics, scripting and more
Extensible skill system — drop new skill folders alongside built-ins or point to them via env vars
Main-thread host adapter — GUI mode uses core
HostUiDispatcherBasesemantics throughBlenderUiDispatcher; headless mode usesBlenderHostwith a coreBlockingDispatcherStreamable HTTP transport — compatible with any MCP 2025-03-26 client
Claude Desktop ready — ship a one-line
mcpServersconfig and you're done
Available MCP Tools
Category | Tools |
blender-scene |
|
blender-objects |
|
blender-mesh |
|
blender-mesh-ops |
|
blender-uv-ops |
|
blender-rigging |
|
blender-pose-library |
|
blender-interchange |
|
blender-export-preset |
|
blender-shot-export |
|
blender-validation |
|
blender-pipeline |
|
blender-materials |
|
blender-shader-nodes |
|
blender-material-library |
|
blender-texture-bake |
|
blender-render |
|
blender-scripting |
|
blender-dev |
|
blender-animation |
|
blender-lighting |
|
blender-light-rig |
|
blender-camera |
|
blender-collection |
|
blender-geometry |
|
blender-geometry-nodes |
|
blender-physics |
|
See src/dcc_mcp_blender/skills/SKILLS_INDEX.md for staged loading guidance, task-to-skill chains, and side-effect profiles for all bundled skills.
Installation
Agent install (recommended)
Want an AI agent to install the Blender-side dependencies, write the MCP host config, and walk you through enabling the add-on? Just ask your agent:
帮我参考 dcc-mcp/dcc-mcp-blender/install.md 去安装The agent follows install.md, which delegates the setup workflow
to skills/dcc-mcp-blender-setup. The remaining
options below are for manual installation.
Option 1 — Install as Blender Extension (ZIP, recommended)
Important: The release ZIP uses the Blender 4.2+ Extension format with
blender_manifest.tomlat the archive root and a flat package layout. Legacy add-on install (Edit → Preferences → Add-ons → Install) will fail with "ZIP packaged incorrectly;__init__.pyshould be in a directory, not at top-level". This is expected — use the Extensions path below. The Extension format is the only supported GUI installation path.
Download the latest platform ZIP from the Releases page:
dcc_mcp_blender_addon_win64_vX.Y.Z.zip,dcc_mcp_blender_addon_linux_vX.Y.Z.zip, ordcc_mcp_blender_addon_macos_vX.Y.Z.zipIn Blender 4.2+: Edit → Preferences → Extensions → Install from Disk… → select the ZIP. (Do NOT use Edit → Preferences → Add-ons → Install — that legacy path is unsupported.)
Enable DCC MCP Blender
The MCP server starts automatically on
http://127.0.0.1:8765
Release ZIPs are Blender 4.2+ Extension packages. They include blender_manifest.toml and the matching dcc-mcp-core wheel under wheels/, so Blender installs the Python dependency into the extension's isolated environment.
The extension ZIP is assembled by packaging/assemble_zip.py. It resolves the latest compatible dcc-mcp-core wheel, places it under wheels/, and injects that wheel into blender_manifest.toml; Blender 4.2+ then installs it through the extension wheel mechanism instead of relying on global pip packages or sys.path edits. See packaging/release_smoke_checklist.md for the manual smoke test procedure.
Option 2 — Install via pip (for scripts / CI)
pip install dcc-mcp-blenderThen in Blender's Python console:
import dcc_mcp_blender
dcc_mcp_blender.start_server()Headless Bootstrap
For CI or automation that needs Blender's main thread dispatcher:
blender --background --python src/dcc_mcp_blender/blender_bootstrap.pyThe bootstrap prints MCP_URL=..., discovers bundled skills, and drives BlenderHost in headless mode until the process is stopped.
In interactive add-on mode, BlenderUiDispatcher subclasses the shared core UI dispatcher and BlenderTimerPump
contains the Blender-specific bpy.app.timers wiring. In background mode, BlenderHost keeps using core
BlockingDispatcher with an explicit headless loop so automation does not depend on Blender UI timers.
Quick Start
Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"blender": {
"url": "http://127.0.0.1:8765/mcp"
}
}
}Make sure the Blender addon is enabled and the server is running, then restart Claude Desktop.
Python API
import dcc_mcp_blender
# Start the server (default port 8765)
dcc_mcp_blender.start_server()
# Stop the server
dcc_mcp_blender.stop_server()Configuration
Environment Variables
Variable | Default | Description |
|
| Set to |
|
| Embedder backend for semantic recall. |
| (none) | Optional timeout in seconds for the readiness probe's dcc verification step. |
Enabling Semantic Skill Recall
# Enable hybrid BM25 + vector recall
export DCC_MCP_BLENDER_SEMANTIC_INDEX=1
# Optional: use ONNX for dense embeddings (better semantic matching)
pip install 'dcc-mcp-core[semantic]'
export DCC_MCP_BLENDER_SEMANTIC_EMBEDDER=onnxWhen enabled, skill search results include a [semantic] extra field and RRF-fused scores.
The feature is opt-in — BM25-only recall remains the default and is not affected when the
env var is unset.
Development
git clone https://github.com/dcc-mcp/dcc-mcp-blender
cd dcc-mcp-blender
pip install -e ".[dev]"
pytestLicense
MIT — see LICENSE for details.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dcc-mcp/dcc-mcp-blender'
If you have feedback or need assistance with the MCP directory API, please join our Discord server