The problem. Cycles on a laptop without a discrete GPU takes minutes per frame; a 240-frame animation is a day. Cloud GPU instances need setup, drivers, a Blender install and a way to move files.
How JANCTION Render works. Send the scene, get the render. No instance, no driver, no Blender install. Each job runs in a disposable container on a JANCTION GPU with Blender 5.0 and Cycles; the container has no network access and is destroyed after the job. A 720p preview takes a few GPU seconds; 24 frames at 720p/64 samples take about a minute end to end.
From the command line.
pip install janction-render export JANCTION_RENDER_SERVER=https://render.janction.jp janction-render preview my_scene.blend --frames 1-24 # 4 frames tiled in one image janction-render render my_scene.blend --frames 1-240 --wait # output.mp4
From an AI agent.
| from | how |
|---|---|
| Claude.ai | Settings → Connectors → Add custom connector → https://render.janction.jp/mcp |
| ChatGPT | Settings → Connectors → Advanced → Developer mode → Create → https://render.janction.jp/mcp (OAuth) |
| Claude Code | claude mcp add --transport http janction-render https://render.janction.jp/mcp |
| Codex | codex mcp add janction-render --url https://render.janction.jp/mcp |
| Cursor and other MCP clients | Streamable HTTP at https://render.janction.jp/mcp; OAuth or Authorization: Bearer <api key> |
Inputs. A .blend (pack external files: File → External Data → Pack Resources) or a bpy Python script that builds the scene. The service sets the engine (Cycles), resolution, samples and denoising; your file sets the scene, camera and frame range. If the scene has no camera or light, an automatic camera and a sun are added and reported in warnings.
JANCTION Render v0.2.1 · JasmyLab Inc.