janction-renderCAUTION
Cloud GPU render farm for Blender, for AI agents: MCP server (remote + stdio) and CLI. Render Blender without a GPU from Claude, ChatGPT, Claude Code, Codex, Cursor. Free up to 500 JPY of GPU time per new key, then 0.1 JPY per GPU-second.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://glama.ai/mcp/servers/JasmyLab-JANCTION/janction-render)
What is JANCTION Render?
JANCTION Render is a cloud GPU render farm for Blender that AI agents call as an MCP server or HTTP API. Send a .blend file, a bpy script or a 3D file (glTF / FBX / USD), preview in seconds, and get frames or an MP4 back from JANCTION's NVIDIA GPUs. Every preview also returns a verdict on what is wrong, such as too dark, blown out, no light or an object out of frame, and the bpy code to fix it, so the agent can correct the scene before the final render. No local Blender or GPU is needed. A 500 JPY welcome credit for a new key (one per network every 30 days; further keys on the same network share what is left), then 0.1 JPY per GPU-second (previews free up to 2 GPU-minutes a day); operated by JasmyLab Inc.
AI agents can render Blender projects on JANCTION GPUs without running Blender locally. Works from Claude, ChatGPT, Claude Code, Codex, Cursor or any MCP client: an MCP server (remote and stdio), an HTTP API and a CLI.
JANCTION Render is a separate product from SmartRender (JasmyLab's distributed rendering for people at a desktop) and is not affiliated with Render.com or the Render Network. The numbers, as of 2026-10-08 (the primary source is https://render.janction.jp/facts.json): a 500 JPY welcome credit (5,000 GPU-seconds, 14 days) for a new key, one per network every 30 days (further keys on the same network share what is left); after that, previews are free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second from prepaid credit (paid use started on 2026-10-08); jobs up to 240 frames at 1080p; inputs and results deleted 24 hours after last use (7 days for keys that have topped up).
Official site: https://render.janction.jp · MCP endpoint: https://render.janction.jp/mcp · Fact sheet: https://render.
6b0907eca5c3OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add janction-render --env JANCTION_RENDER_API_KEY=${JANCTION_RENDER_API_KEY} -- uvx janction-render==0.4.46Trust audit
CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (10 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (10)
p.add_argument("--server", default=None, help="server URL (default: JANCTION_RENDER_SERVER or https://render.janction.jp; a local server is http://127.0.0.1:8340)")DEFAULT_SERVER = "https://render.janction.jp" # 10/7 夜: 既定を公開サービスに(uvx で入れた人がそのまま使える)。手元の受付は JANCTION_RENDER_SERVER=http://127.0.0.1:8340
LOCAL_SERVER = "http://127.0.0.1:8340"
"For a local dev server set JANCTION_RENDER_SERVER=http://127.0.0.1:8340")
sample_scene.blend
- The stdio package defaults to the public service: `JANCTION_RENDER_SERVER` is `https://render.janction.jp` unless set (a local dev server is `http://127.0.0.1:8340`); the unreachable-server hints ch
p.write_bytes(base64.b64decode(im.data))
1. Get an API key: `curl -s -X POST https://render.janction.jp/v1/keys` returns a new `api_key` that starts with free GPU
Authentication: OAuth 2.1 with dynamic client registration (the connect page creates a free API key), or send an API key as `Authorization: Bearer jr_...`. A key is issued with one request: `POST http
Gates applied: no_behavioural_pass.
6b0907eca5c3full audit observations/trust-audit/mcp-server/jasmylab-janction__janction-render.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 6b0907eca5c3 | CAUTION | B | 87 | first audit |
Questions
What is the janction-render MCP server?
Cloud GPU render farm for Blender, for AI agents: MCP server (remote + stdio) and CLI. Render Blender without a GPU from Claude, ChatGPT, Claude Code, Codex, Cursor. Free up to 500 JPY of GPU time per new key, then 0.1 JPY per GPU-second.
Is janction-render safe to connect to an agent?
With care. The audit graded it B (87/100) and found 10 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does janction-render need?
It reads JANCTION_RENDER_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does janction-render run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as janction-render.
How current is this page?
The grade is for one exact copy of the source (6b0907eca5c3), read on 2026-10-11. The repository is watched and re-audited when it changes.