Render Blender scenes (.blend or a bpy Python script) on JANCTION GPUs straight from a terminal AI agent (Claude Code, Codex, or any MCP client). Use it when you are building 3DCG with Blender and have no GPU, or rendering locally is slow. Free beta: nothing is charged. Inputs and results are deleted 24 hours after last use and are never used for training.
claude mcp add janction-render -e JANCTION_RENDER_SERVER=https://render.janction.jp -- uvx --from janction-render janction-render-mcp
Codex: put the same command in ~/.codex/config.toml (see the README on GitHub).
A temporary API key is issued automatically on first use; set JANCTION_RENDER_API_KEY to keep one.
| tool | what |
|---|---|
| scene_info | read the scene without rendering: cameras, frame range, resolution, missing files |
| render_preview | fast preview, 1-4 frames tiled in one image (720p budget), returned inline |
| render_final | final frames or an MP4, split across GPUs |
| render_status / render_download / render_cancel | progress, files, cancel |
| billing | free-beta quota (later: balance, price, top-up link) |
Free beta: nothing is charged. Limits: 10 GPU-minutes per key per day (20 per network), final renders up to 240 frames and 1080p. When the daily quota is used up the API answers 429 quota_exceeded with resets_at. Planned pricing (0.1 JPY per GPU second, top-up from 500 JPY) will be announced here and in llms.txt before it starts.
POST /v1/keys temporary key (no sign-up)
POST /v1/files (multipart file) .blend or .py -> scene_id
POST /v1/jobs {scene_id, kind: info|preview|final, ...}
GET /v1/jobs/{id} status, artifacts, cost
GET /v1/jobs/{id}/artifacts/{name}
llms.txt (the guide agents read first) · Security · GitHub
JANCTION Render v0.1.0 · JasmyLab Inc.