Claude Code + Blender rendering

Add the JANCTION Render MCP server to Claude Code (one command), then ask for a scene. Claude Code writes the bpy script, previews it on a JANCTION GPU in a few seconds, fixes it, and renders the final frames or MP4. No local GPU and no local Blender needed. Each new key starts with a welcome credit of up to 500 JPY (100 JPY with no card, 400 JPY more after registering a card, which is not charged) (14 days); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second. AI agents connect at https://render.janction.jp/mcp (remote MCP with OAuth; connecting creates a free key).

Updated 2026-11-12

What it does From an AI app over MCP: the bpy script the AI wrote, or your own .blend or 3D file, rendered on a cloud GPU. Preview, fix, estimate, then the final. The price is shown before rendering, and a paid render starts only after you approve it. Without a connector, let the AI write the script and paste it at /start.
What it does not do Not a tool for editing 3D inside that app (a local Blender is driven by a separate MCP such as blender-mcp). Until it is connected and authenticated, the AI cannot render.

Paste your AI's script and try Try your own file for free

Browser only; no connector or CLI needed. A 100 JPY welcome credit for a new key (14 days, no card; one per network every 30 days, further keys on the same network share what is left), and 400 JPY more for saving a card that is not charged (once per card); after that, previews stay free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second.

Setup

# remote (nothing to install; OAuth creates a free key)
claude mcp add --transport http janction-render https://render.janction.jp/mcp

# or stdio (sends local files, saves results locally)
claude mcp add janction-render -e JANCTION_RENDER_SERVER=https://render.janction.jp -- uvx --from janction-render janction-render-mcp

# plugin with the workflow skill
/plugin marketplace add JasmyLab-JANCTION/janction-render
/plugin install janction-render@janction-render

Claude Code on the web (cloud sessions)

Connect JANCTION Render as a claude.ai connector. Nothing else to change:

On claude.ai: Plugins (older menu: Customize → Connectors) → Add custom connector.
URL: https://render.janction.jp/mcp, then Connect. The page that opens creates a free key.
In the cloud session, ask: "Render a test scene with janction-render." A preview comes back in a few seconds.

Claude Code sends the bpy script it writes as scene_script and a file on the web as scene_url. Open the result links in your browser.

Why: a cloud session reaches only allowed domains, and render.janction.jp is not on the default list, so curl or the janction-render command gets a 403 from the session's proxy (NETWORK_BLOCKED). The service is not down. Connector traffic goes through Anthropic, not the session's network.

A .blend that exists only inside the session: allow the domain instead. On claude.ai/code, open the environment selector, click the environment's settings icon, choose Network access → Custom, add render.janction.jp under Allowed domains (keep the defaults) and save. A running session follows within about a minute.

Then ask

Using JANCTION Render, build a glossy red cube rotating on a gray floor and show me a 4-frame preview.
If it looks right, render 24 frames at 1280x720 as an MP4.

To render a .blend or 3D file that is on your computer, drop it at /upload to get a 12-hour link (no sign-up) and tell the AI "Render this file: <link>". To test the connection first: "Render a preview of https://render.janction.jp/samples/cube_scene.py".

Or: "Build a small street scene in Blender with a camera fly-through and render a 24-frame preview with janction-render."

What Claude Code does

scene_info reads the scene without rendering: cameras, frame range, objects, missing files.
render_preview renders 1-4 frames at 720p in a few GPU seconds and returns the image, so the agent can look, fix the script and try again.
render_estimate says how long the final render takes ("about 3 minutes") and whether it fits the free GPU time left (the welcome credit while it lasts, then up to 2 preview GPU-minutes a day).
render_final renders the frames on GPUs and joins them into an MP4; render_status reports the remaining time; render_download returns the files or links.

A 4-frame preview rendered by JANCTION Render (a rotating red cube) — The 4-frame preview Claude.ai got from that prompt: 4 GPU seconds. The 24-frame 720p MP4 that followed took 58 GPU seconds (2026-10-01, RTX PRO 6000).

How long it takes

job	GPU time	note
preview, 4 frames (720p split in 4 tiles, 16 samples, denoised)	about 4 s	round trip about 8 s; the image comes back inline
final, 24 frames at 1280x720, 64 samples → MP4	about 60 s	measured 2026-09-30 / 10-01 (59 s and 58 s)
final, one 1920x1080 frame at 128 samples	about 11 s	the estimator's baseline; heavy scenes take longer

These are individual observations of simple scenes (2026-09-30 to 10-01 UTC, NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, 96 GB). The 4-GPU-second example used a rotating cube, four 640x360 tiles and 16 samples. GPU time includes Blender startup and scene loading; it is distinct from completion time including queue and transfers. See conditions, round trips and reproduction files. These are not speed guarantees.

render_estimate gives the number before rendering; once a scene has been rendered once, the estimate uses that scene's own measurement.

Tips for scripts

Add a camera and a light and set the frame range; do not change render settings or call bpy.ops.render.render.
Animate with obj.keyframe_insert(); action.fcurves was removed in Blender 5.0.
Do not set Material.use_nodes (always on in 5.x). Procedural materials work; image textures are sent as assets or packed into a .blend.
Pass environment='studio' (or sunset / overcast / night) for HDRI lighting when you have not set up lights.
Sample: cube_scene.py.

Free limits

Pricing (since 2026-10-08): Each new key gets 100 JPY of GPU time free with no card (1,000 GPU-seconds, 14 days) for previews and finals, and 400 JPY more once a card is saved on a Stripe page that charges nothing (once per card): up to 500 JPY in all. After it is used up or expires, previews are free up to 2 GPU-minutes per key per day and final renders are paid from prepaid credit at 0.1 JPY per GPU-second. Top-ups (paid) start at 100 JPY. The first top-up during the 14-day welcome period counts 1.5x, with the bonus capped at 500 JPY (100 JPY buys 150 JPY of credit). Top-ups of 2,000 JPY or more get 10 to 20% extra (not combined with the first-top-up bonus; the larger one applies). Top-up bonuses are separate from the welcome credit and the card-saving credit. Payment is on a Stripe Checkout page. One full welcome credit per network every 30 days; further keys from the same network use what is left of that network's credit. A job without enough credit gets HTTP 402 payment_required with a checkout_url. Final renders go up to 3,000 frames per instruction (automatically split internally under one job id), 1080p (1920x1080) on free time and up to 4K (3840x2160) on prepaid credit. The free preview time resets at 00:00 UTC (09:00 JST). No sign-up: connecting creates a key. Inputs and results are deleted 24 hours after last use (normally 7 days for keys that have paid 500 JPY or more in total) and never used for training.

Without a connector

If you cannot add a connector to your AI (plan or administrator settings), the same result is one step away: send the prompt below to the AI and paste the code it returns into the paste-and-render page. The preview needs no payment.

Write a Blender 5.0 bpy script that builds <describe your scene here>. Add a camera and set scene.camera, and add one light. Do not call render and do not change render settings. Reply with the code only.

To fix something, give the AI the preview's notes (too dark, cut off, no light) and paste the rewritten script again.

FAQ

Does Claude Code need Blender installed?

No. Claude Code writes a bpy script as text and sends it; Blender runs on the JANCTION GPU.

Remote or stdio: which one?

Remote if you want nothing to install and links as results. stdio if you want to send local .blend files with their textures and save results next to your project.

What if the render fails?

The job carries the Blender log tail and warnings; Claude Code reads them, fixes the script and previews again. Missing cameras and lights are added automatically.

Claude Code on the web says 403 for render.janction.jp. Is the service down?

No. The cloud session's network allows only listed domains. Use the JANCTION Render connector from claude.ai, or add render.janction.jp to the environment's Allowed domains (Network access → Custom); a running session follows within about a minute.

Overview · All guides · llms.txt