Updated 2026-10-05
In Cursor, add the MCP server https://render.janction.jp/mcp (the button below or Settings → Tools & MCP → Add). Cursor's agent then has 12 render tools: it writes a bpy script, calls render_preview, looks at the image, fixes the scene, and calls render_final for the MP4. Free beta: 10 GPU-minutes per key per day.
One click: Add to Cursor Add to VS Code. Cursor opens, shows the server, and you confirm. The first tool call opens the OAuth consent page, which creates a free key.
By hand, in ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project):
{
"mcpServers": {
"janction-render": { "url": "https://render.janction.jp/mcp" }
}
}
Settings → Tools & MCP should list janction-render with 12 tools (scene_info, render_preview, render_estimate, render_final, render_status, render_download, render_cancel, render_share, render_unshare, asset_search, billing, render_info). If the auth step did not open, click the server and choose Login.
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".
Or, with an existing file: "Upload scene.blend from this project to JANCTION Render, preview frame 1, then render frames 1-48 at 1080p as an MP4." (Remote tools take an https URL or a bpy script; to send a local .blend from Cursor, let the agent run the CLI: pip install janction-render, then janction-render render scene.blend --frames 1-48 --wait.)
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 today's free quota.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.| 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.
401 on the first call: finish the OAuth consent in the browser window Cursor opened; a free key is created there.429 quota_exceeded: today's 10 GPU-minutes for this key are used; the response carries resets_at. 400 beta_limit: split the job (240 frames and 1080p per job during the beta).environment='studio' or add a camera and a sun (see bpy rules).Delete the janction-render entry from mcp.json (or the server from Settings → Tools & MCP). To revoke the key the consent page created: POST https://render.janction.jp/v1/keys/revoke with the key, or disconnect the app under /v1/connections.
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.
No. The remote MCP server runs Blender 5.0 on a JANCTION GPU; Cursor only writes the script and calls the tools.
The remote tools take an https URL or a bpy script. For a local .blend, let the agent use the CLI (pip install janction-render) or the stdio MCP server, which uploads the file.
Yes. It is a cursor:// deep link; Cursor opens and asks you to confirm the server. If nothing happens, paste the mcp.json entry instead.
Nothing during the free beta: 10 GPU-minutes per key per day. The planned price is on the pricing page and in every estimate (list_price_yen).
JANCTION Render v0.4.17 · JasmyLab Inc. · Updated 2026-10-05 · Tested with Blender 5.0, JANCTION Render 0.4.17 · 日本語