RenderBuddy
Enables monitoring and control of Blender renders via natural language, providing real-time render status, settings, preview frames, and protected actions like cancellation.
README
RenderBuddy MCP v2.0
"Your render, one message away."
RenderBuddy MCP is a Blender-native Model Context Protocol (MCP) tool. Artists install the RenderBuddy Blender Add-on, enable it in Blender, and can immediately talk to their active renders in natural language using any MCP client (Claude Desktop, Cursor, Antigravity, VS Code) without manual path configuration.
What's New in v2.0 (Blender Add-on Architecture)
- Zero-Setup Workflow: No need to configure
.blendfile paths or Blender executable paths in TOML! Blender (via the add-on) is the live source of truth. - Blender N-Panel & Properties UI: View connection status, port settings, and generate security PIN hashes directly inside Blender's interface.
- Local HTTP REST API (Port 7342): Pure Python
http.serverrunning on a background daemon thread inside Blender exposes live render state instantly over loopback. - Safe Main-Thread Execution: Render cancellations are queued and safely executed on Blender's main thread via
bpy.app.timers. - Cross-Platform: Full support for Windows, macOS, and Linux out of the box.
How It Works
┌───────────────────────────┐ ┌───────────────────────────┐
│ Blender 3.6+ │ │ MCP Server Proxy │
│ ┌─────────────────────┐ │ GET /status │ ┌─────────────────────┐ │
│ │ RenderBuddy Add-on │◄─┼────────────────┼──│ AddonClient │ │
│ │ (bpy.app.handlers) │ │ POST /cancel │ │ (services/addon) │ │
│ └──────────┬──────────┘ │ │ └──────────┬──────────┘ │
│ │ │ │ │ │
│ ▼ │ │ ▼ │
│ [HTTP Server:7342] │ │ [MCP Tool Handlers] │
└─────────────┬─────────────┘ └─────────────┬─────────────┘
│ │
└─────────────────── Loopback ───────────────┘
(127.0.0.1)
Quick Start Guide
1. Install & Enable the Blender Add-on
- Run the build script to generate
dist/renderbuddy_addon.zip:python build_addon.py - In Blender: Edit → Preferences → Add-ons → Install...
- Select
dist/renderbuddy_addon.zipand check the box to Enable RenderBuddy.
2. Install the MCP Server
pip install -e .[dev]
3. Add to your MCP Client Configuration
In your client configuration file (mcp_config.json or claude_desktop_config.json):
{
"mcpServers": {
"renderbuddy": {
"command": "python",
"args": [
"C:/path/to/RenderBuddy/main.py"
]
}
}
}
4. Start Rendering & Ask Anything!
Open any project in Blender, press Render, and ask your AI assistant:
- "How is my render going?"
- "Show me the latest rendered frame."
- "How much time is left?"
- "What resolution am I rendering?"
- "Cancel the render (PIN: 1234)"
MCP Tools Reference
SAFE Tools (No Authentication Required)
| Tool | Description | Example Query |
|---|---|---|
ping() |
Health check verifying MCP server and Blender add-on connection | "Ping RenderBuddy" |
server_info() |
Returns server version and architecture details | "What version is running?" |
render_status() |
Returns progress %, frame counts, state, engine, and ETA | "How's the render going?" |
render_settings() |
Returns resolution, frame range, camera name, and format | "What resolution am I rendering?" |
preview_frame() |
Returns path and details of the latest rendered frame image | "Show me the latest frame" |
upload_render() |
Exports latest frame or .blend file to local folder |
"Upload the finished render" |
email_render() |
Dispatches email with attached render output | "Email me the render" |
PROTECTED Tools (PIN Authentication Required)
| Tool | Requirements | Example Query |
|---|---|---|
cancel_render(pin) |
Valid PIN | "Cancel the render, PIN 1234" |
shutdown_pc(pin, confirm) |
Valid PIN + confirm="SHUTDOWN" |
"Shut down my PC after rendering" |
Running Automated Tests
Run the full 107+ unit test suite (runs standalone without requiring Blender):
python -m pytest -v
License
MIT License. Designed for 3D Artists, Studios, and Pipeline TD Automation.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.