Codex and Claude Code MCP setup for JANCTION Render, and the limits that are easy to miss

#blender #mcp #codex #claude

JANCTION Render (https://render.janction.jp) renders AI-written scenes and existing .blend files on a cloud GPU. It is a separate product from SmartRender, JasmyLab's distributed-GPU platform.

Add https://render.janction.jp/mcp and an agent can render a Blender scene on a cloud GPU. As of 2026-10-02 the beta is free: no sign-up and no card. You need an MCP client that allows a custom remote server. The quota is 10 GPU-minutes per key per day and 20 per network. A job past that limit is rejected with HTTP 429 quota_exceeded and resets_at. It is not queued until the next day, and splitting the job does not increase the daily quota. Resubmit after 00:00 UTC (09:00 JST). One job may be at most 240 frames at 1080p.

This post is from JasmyLab, the operator of JANCTION Render. The service is a beta on one shared GPU, with no availability guarantee. The inference API on the same machine has priority.

Site: https://render.janction.jp
Repository: https://github.com/JasmyLab-JANCTION/janction-render

What this MCP is

It renders. It does not model the scene that is open in your desktop Blender. A local Blender MCP does that, and it does not require a discrete GPU: Cycles can render on a CPU. JANCTION Render accepts a .blend, a bpy script, or a 3D file (glTF, FBX, USD, OBJ, STL, PLY, Alembic), runs Blender on a datacenter NVIDIA GPU, and returns a preview, frames, or an MP4.

Default Blender is 5.0. Pass blender="5.2" when render_info or /v1/health lists 5.2. On 2026-10-02 the public health endpoint listed both. The default engine is Cycles. Final jobs can set engine='eevee'; each EEVEE job pays a shader-compile overhead, so short previews stay on Cycles.

Codex

codex mcp add janction-render --url https://render.janction.jp/mcp

Authentication is OAuth. The consent page creates a free key. If the client cannot open a browser, a raw API key from POST /v1/keys also works as Authorization: Bearer.

There is a plugin marketplace entry on the same GitHub repository (codex plugin marketplace add JasmyLab-JANCTION/janction-render). Marketplace install and a successful render are different checks. Confirm with render_info before you trust a render.

Prompt that matches the published sample:

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

Claude Code

claude mcp add --transport http janction-render https://render.janction.jp/mcp

Then /mcp and authenticate. The same prompt works. Claude.ai's custom connector is a separate path (Settings → Connectors) and depends on the plan. Team and enterprise admins can disable custom MCP servers. Do not treat "it works in Claude Code" as "it works in every Claude surface."

Setup pages:

A render, not a Blender session

The useful order is fixed:

scene_info reads cameras, frame range, and missing files without rendering.
render_preview returns 1–4 frames. The published 4-tile example (rotating cube, 640×360 tiles, 16 samples) was about 4 GPU seconds. The round trip that day was about 8 seconds. Those are different clocks.
render_estimate returns a duration and whether the job fits today's quota.
render_final renders frames and can join an MP4. render_download returns files or 24-hour links.

GPU seconds include Blender startup and scene load on the worker. They are not "GPU chip only," and they are not the time from your keypress to the file on disk. Queue wait is extra. Whether the upload is inside the round-trip number depends on the path; do not assume every published case includes it.

A 24-frame 1280×720 MP4 at 64 samples was about 58.7 GPU seconds, with a round trip around 65 seconds, on an NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition (96 GB). That scene is simple. Volumes and large textures will not scale the same way. Figures: https://render.janction.jp/benchmarks and https://render.janction.jp/benchmarks.json

What fails in ordinary use

A .blend saved in a newer Blender than the worker you selected.
Unpacked image textures. Pack them, or send them as assets. Missing textures render pink.
Asking for more than 240 frames or above 1920×1080 in one free-beta job (beta_limit). Split that job. Do not split in order to get more than 10 GPU-minutes today.
Custom add-ons. The worker is stock Blender 5.0 or 5.2 plus the bundled HDRI presets and standard importers.
Treating Colab, SheepIt, or Sceneplane as the same product. Colab's official FAQ does not promise a T4 or a 90-minute idle timeout. SheepIt has no MCP. Sceneplane's free tier, checked 2026-10-02, is 30 compute minutes per month and includes scene work, not a GPU-second quota. https://sceneplane.online/

Nothing is billed during this beta. Pages that mention 0.1 JPY per GPU second are describing a planned rate, not an invoice.

DEV Community