Vol. 1 · No. 338Blender 3.6 / 4.2 / 4.5 / 5.0 / 5.2 / 5.3Cycles · EEVEE
JANCTION
Render · Blender on RTX PRO 6000 · Tokyo
0.1 JPYper GPU-secondFirst 100 JPYfree, no card
Front page / VS Code (Copilot agent mode) + Blender rendering

VS Code (Copilot agent mode) + Blender rendering

Install the server with the VS Code button below or add it to .vscode/mcp.json as type http with the URL https://render.janction.jp/mcp. In Copilot Chat choose Agent mode; the 13 janction-render tools appear under the tools icon. Ask for a scene, approve the tool calls, and the preview image comes back in the chat.

Updated 2026-11-17

What it does Your own .blend, bpy script or 3D file (glTF/GLB, FBX, USD, OBJ...) rendered to images or video on a cloud NVIDIA GPU, from an AI app, the terminal or the browser. The first preview needs no payment.
What it does not do It does not speed up the Blender viewport on your machine, does not take non-Blender video, simulations or general GPU jobs, and an AI that is not connected cannot render on its own.

Paste your AI's script and tryTry 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

One click: Add to Cursor Add to VS Code Add to LM Studio (the VS Code link uses vscode:mcp/install). Or run code --add-mcp '{"name":"janction-render","type":"http","url":"https://render.janction.jp/mcp"}'. Or write .vscode/mcp.json in the workspace:

{
  "servers": {
    "janction-render": { "type": "http", "url": "https://render.janction.jp/mcp" }
  }
}

Run MCP: List Servers from the Command Palette and start the server; the first tool call opens the OAuth consent page in your browser (a free key is created). VS Code 1.102 or later ships MCP support; earlier versions need the Insiders build or an update.

Then ask (Copilot Chat → Agent)

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".

Copilot asks before each tool call the first time; choose Always allow for the janction-render tools if you want the preview → fix → final loop to run without clicks.

What happens

  1. scene_info reads the scene without rendering: cameras, frame range, objects, missing files.
  2. 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.
  3. 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).
  4. 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

jobGPU timenote
preview, 4 frames (720p split in 4 tiles, 16 samples, denoised)about 4 sround trip about 8 s; the image comes back inline
final, 24 frames at 1280x720, 64 samples → MP4about 60 smeasured 2026-09-30 / 10-01 (59 s and 58 s)
final, one 1920x1080 frame at 128 samplesabout 11 sthe 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.

Troubleshooting

  • Tools do not appear: open the tools picker in the chat input and tick janction-render; agent mode must be selected (not Ask or Edit).
  • "Server failed to start": the entry must be "type": "http" with the URL above; sse is not used.
  • Consent page never opened: run MCP: List Servers → janction-render → Start; VS Code prints the auth URL in the output panel.
  • quota_exceeded or beta_limit: see the free limits below; split long animations across jobs.

Remove

MCP: List Servers → janction-render → Uninstall, or delete the entry from mcp.json. Revoke the key with POST https://render.janction.jp/v1/keys/revoke if you want the consent page's key gone too.

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-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

Which VS Code version do I need?

MCP servers are supported in VS Code 1.102 and later (GitHub Copilot Chat in agent mode).

Does this work without GitHub Copilot?

The MCP server is generic, but VS Code's built-in agent that calls MCP tools is Copilot Chat. Other VS Code agents that speak MCP can use the same entry.

Can I use a plain API key instead of OAuth?

Yes: add a header Authorization: Bearer jr_... to the server entry (VS Code supports headers for http servers). A key comes from POST /v1/keys.

Related

Overview · All guides · llms.txt