JANCTION Render

JANCTION Render is a cloud GPU render farm for Blender that AI agents call as an MCP server or HTTP API.

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

  • Render Preview: Show what a Blender scene looks like: a fast, low-cost preview render on a cloud GPU, back as an image in seconds. Typical requests: 'render this .blend', 'show me the scene', 'preview
  • Render Final: Render the final frames or video of a Blender scene on cloud GPUs, after the user approved a preview: 'render the final', 'make the video', 'export the turntable MP4', 'product shots fro
  • Render Download: Get the download links of a job (no key needed, valid about 24 hours) and show them to the user; in a terminal, fetch them with curl -o. A finished preview also comes back as an inlin

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

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. No local Blender or GPU is needed.

Как подключить

Как подключить JANCTION Render к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://janction-render.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить JANCTION Render к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://janction-render.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить JANCTION Render к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://janction-render.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (12)

Технические названия из tools/list. Нужны только разработчикам.

render_previewShow what a Blender scene looks like: a fast, low-cost preview render on a cloud GPU, back as an image in seconds. Typical requests: 'render this .blend', 'show me the scene', 'preview the turntable', 'I have no GPU', 'Blender is too slow on my laptop', 'Blenderでレンダリングして', 'GPUがない', 'ターンテーブル', '商品の360度動画'. Also use it after writing a bpy script, to see what it builds. Each preview returns a critic verdict (ok / check / fix) with fix code: apply the fixes and preview again before any final render. It also returns final_estimate (the same scene as a 1080p final) and quota_left_today; tell the user both before asking to go on. When not to use: editing a scene open in the user's Blender belongs to a local Blender MCP, and a single still on a machine with its own NVIDIA GPU usually renders faster locally. This service is for CPU-only machines, animations, and scripts with no Blender installed. Limits: up to 1280x720; 1-4 frames tiled in one labeled image for the GPU time of one 720p frame. Options are explained on each parameter: environment presets and 'compare', orbit (turntable), cameras (several named cameras), engine, transparent, asset_urls with 'polyhaven:<id>' CC0 assets. Give the scene as scene_script (bpy code as text), scene_url (an https link to a .blend, .py or 3D file) or scene_id; reuse the returned scene_id in render_final.
render_finalRender the final frames or video of a Blender scene on cloud GPUs, after the user approved a preview: 'render the final', 'make the video', 'export the turntable MP4', 'product shots from these cameras'. Call render_estimate first when the time or the free GPU time left (the welcome credit, or 2 preview GPU-minutes a day after it) is uncertain, the job is longer than about 24 frames or above 720p, or the user asks how long it takes, and tell the user. Long jobs are rendered in chunks and joined into one video. Returns job_id and estimate.human at once (short jobs return the links directly); then call render_download(job_id, wait_seconds=45). When not to use: editing a scene open in the user's Blender belongs to a local Blender MCP, and a single still on a machine with its own NVIDIA GPU usually renders faster locally. Use the same environment and blender as the approved preview. Limits: up to 240 frames and 1920x1080 per job; each new key gets 500 JPY of GPU time free (welcome credit, 14 days); after that, previews are free up to 2 GPU-minutes a day and finals cost 0.1 JPY per GPU-second (prepaid); ask the user before a render that the free time does not cover; files are deleted 24 hours after last use. Options are explained on each parameter: output (png, exr, mp4, webm, prores, gif, webp), orbit=True for a turntable MP4, cameras for one image per named camera, transparent, engine='eevee', notify_url for one POST when the job finishes, asset_urls with 'polyhaven:<id>'. Pass scene_id from render_preview, or scene_script / scene_url for a new scene.
render_downloadGet the download links of a job (no key needed, valid about 24 hours) and show them to the user; in a terminal, fetch them with curl -o. A finished preview also comes back as an inline image. wait_seconds > 0 first waits for the job (the service waits at most 50 s per call; call again while it is still running). only picks the files: 'output' (default: the MP4 or the preview sheet, plus the first frames), 'mp4', 'sheet', 'frames' or 'all'.
render_statusCheck a render job: status (queued / running / done / failed / canceled), frames done, the ETA (eta.human, including queue wait), files ready, Blender warnings, and the error with the log tail if it failed. Use it to report progress to the user; render_download(job_id, wait_seconds=45) waits and returns the links in one call.
scene_infoRead a Blender scene without rendering (a few seconds, no GPU time): cameras and the active one, frame range and fps, resolution, objects by type, lights, materials, whether it is animated, and missing linked files that would render pink. Use it for a .blend you did not write, or to check what a bpy script built. Returns scene_id; pass it to render_preview and render_final instead of sending the scene again.
render_estimateEstimate a render before starting it (no GPU time): GPU seconds, queue wait, the wall-clock time as text (estimate.human, e.g. 'about 3 minutes') and whether it fits the free GPU time left (the welcome credit, or 2 preview GPU-minutes a day after it) and the size limits. Call it before render_final when the time or quota is uncertain, the job is longer than about 24 frames or above 720p, or the user asks how long it takes; tell the user the result. With scene_id the estimate uses this scene's measured render times; it also says when to split a job.
render_infoShow the JANCTION Render service state: whether GPU workers are online, queue length and expected wait, this key's usage, and how to connect from other clients. Call this if renders seem stuck or before the first render. Use it to decide whether to route a render here: workers_available > 0 means a preview comes back in seconds; gated means the GPU is lent out and 'gate' says how long the wait usually is.
asset_searchFind free CC0 3D models, PBR textures or HDRIs on Poly Haven by words ('wooden chair', 'forest hdri') to furnish a scene without uploading files; no GPU time. Each result has a spec 'polyhaven:<id>' to pass in asset_urls, its size in metres and the entry file. In the scene script: import jr_assets, then jr_assets.import_model('<id>', location=(x, y, z), scale=1.0) returns the objects, jr_assets.material('<id>') builds a material and jr_assets.apply(obj, mat) assigns it, jr_assets.world_hdri('<id>', strength=1.0) lights the world. 'polyhaven:<id>@2k' fetches 2k textures (1k by default).
render_sharePublish a finished render as a public page the user can send to anyone (X, Discord, a client): the image or video, the render conditions, an optional title and note, and the bpy script if include_script=True. The page keeps a copy of the result after the job's 24-hour expiry, until render_unshare. listed=True asks for it to appear in the public gallery (/gallery) after the operator reviews it; until then the page is not indexed by search engines. prompt: what the user asked you, in their words (shown as 'what the user asked the agent'; it makes the page useful to others). Ask the user before sharing; return the url to them.
render_unshareRemove the public share page of a job (the copy of the result is deleted).
render_cancelCancel a queued or running JANCTION render job. GPU time after the cancel is not used.
billingCheck the free GPU time left and the credit: what this key can still render for free (a new key's welcome credit, or the free daily amount), when it resets or expires, plus the balance (yen), the price per GPU second and any pending checkout link. Jobs the free time covers cost nothing; beyond it only the extra GPU seconds are charged from prepaid credit. Also shows auto top-up and monthly plan status, with links the user can open to turn them on.