blender-llm-mcp
MCP (Model Context Protocol) server for Blender 3D — expose Blender modeling tools to AI assistants via the Model Context Protocol.
GitHub: WeitaoYan/blender-llm-assistant
Overview
blender-llm-mcp is the MCP server component of the Blender LLM Assistant project. It acts as a bridge between AI assistants (Claude Desktop, VS Code, etc.) and the Blender 3D software.
This package alone is NOT enough — it requires the Blender LLM Assistant addon to be installed and running inside Blender. The addon exposes an HTTP API on 127.0.0.1:15800, and this MCP server translates MCP tool calls into HTTP requests to that API.
Architecture
AI Assistant (Claude / VS Code)
│ MCP stdio protocol
▼
blender-llm-mcp (this package)
│ HTTP + SSE, Bearer Token auth
▼
Blender LLM Assistant addon ← must be running in Blender
│ Blender Python API (bpy)
▼
Blender 3D scene
Usage
Requires the Blender LLM Assistant addon running in Blender (HTTP API on 127.0.0.1:15800).
The Blender addon uses Bearer Token authentication. After starting the server in Blender, copy the token from the panel and pass it to the MCP server.
# Install
pip install blender-llm-mcp
# Run with token
blender-llm-mcp --blender-token <token-from-blender-panel>
# Or with uvx (no install needed)
uvx blender-llm-mcp --blender-token <token-from-blender-panel>
# Custom Blender URL
blender-llm-mcp --blender-url http://127.0.0.1:15800 --blender-token <token>
Configuration in Claude Desktop
First set the token as an environment variable, then reference it in the config:
export BLENDER_TOKEN="<token-from-blender-panel>"
Add to your claude_desktop_config.json:
{
"mcpServers": {
"blender": {
"command": "uvx",
"args": ["blender-llm-mcp", "--blender-token", "${BLENDER_TOKEN}"]
}
}
}
How it works
Claude Desktop / VS Code / any MCP client
│ MCP stdio protocol
▼
blender-llm-mcp
│ HTTP (SSE)
▼
Blender LLM Assistant addon (inside Blender)
│ Blender Python API (bpy)
▼
Blender 3D scene
The MCP server translates MCP tool calls into HTTP requests to the Blender addon.
Metadata
Release files for blender-llm-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| blender_llm_mcp-0.1.1.tar.gz | 5.4 kB | Without provenance | Details for blender_llm_mcp-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| blender_llm_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for blender_llm_mcp-0.1.1-py3-none-any.whl |
Total release size: 11.6 kB
Release files / blender_llm_mcp-0.1.1.tar.gz
| Download URL | blender_llm_mcp-0.1.1.tar.gz |
|---|---|
| Size | 5.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a3ca1d1b7542b43d39086b2268a06b98c184d18040eb43f76ec17405e354b857
|
|
BLAKE2b-256 checksum How to use checksums |
27db5f265c408befb4c4c8a505e5f3dd777fd9ff19b59efb9616b8e962c97d6c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / blender_llm_mcp-0.1.1-py3-none-any.whl
| Download URL | blender_llm_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 6.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
424a29fd030577cadff871b0295a972231e4932b6f8f09e506d8c26018038770
|
|
BLAKE2b-256 checksum How to use checksums |
b2ea4be134d602535b3cc4639a9a782b2edd29058fa836d5f6730379cabfb00f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for blender-llm-mcp 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.