VS Code (Copilot agent mode) + Blender rendering

Updated 2026-10-05

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 12 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.

Setup

One click: Add to Cursor Add to VS Code (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 grey 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 today's free quota.
  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

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

Free beta (as of 2026-10-01): 10 GPU-minutes per key per day (20 per network), final renders up to 240 frames at 1080p. Quotas reset at 00:00 UTC (09:00 JST). New jobs exceeding the quota are rejected with HTTP 429 quota_exceeded and resets_at; they are not queued for the next day. Resubmit after the quota resets. No sign-up: connecting creates a key. Inputs and results are deleted 24 hours after last use and never used for training. Paid plans will be announced on this site and in llms.txt before they start.

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 · llms.txt

JANCTION Render v0.4.17 · JasmyLab Inc. · Updated 2026-10-05 · Tested with Blender 5.0, JANCTION Render 0.4.17 · 日本語