com.budgetpixel/mcp

Est-ce que com.budgetpixel/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.budgetpixel/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 18 outils

• check_generation_status≈ 574 tokens

  Use this after calling generate_image, generate_video, generate_music, generate_sound_effect, generate_3d_model, or generate_depth_map to poll for results. Pass a job_id to check a specific job — numeric = image, uuid = video, and for MUSIC / SOUND-EFFECT / 3D-MODEL / DEPTH-MAP jobs also pass type "music" / "sound_effect" / "3d" / "depth" (3D jobs are uuids too, like video) — with no job_id it lists jobs still running that were started on the BudgetPixel website. Completed IMAGE jobs return the finished image(s) inline (as image content) plus a full-resolution link — display the image AND share the link (some chat UIs don't show inline images). Completed VIDEO, MUSIC and SOUND-EFFECT jobs return a watch/listen link — always share it with the user (chat UIs can't embed players). Completed 3D-MODEL jobs return the thumbnail inline plus download links (GLB/FBX/USDZ/STL) and a viewer link — share the links and tell the user downloads expire in about 24 hours. Completed DEPTH-MAP jobs return the depth video, which is saved in the user's BudgetPixel library. Poll every few seconds for images and sound effects (~15 s), every 15–30 seconds for videos, music, 3D models and depth maps (they take minutes). Call repeatedly until status is 'completed' or 'failed'.

  Paramètres, retour & exemple (2)

  Paramètres

  • type · string · optionnel · image | video | music | sound_effect | 3d | depth
    Which pipeline the job_id belongs to. REQUIRED as "music" for music jobs, "sound_effect" for sound-effect jobs, "depth" for generate_depth_map jobs (their numeric ids would otherwise be read as image jobs), and "3d" for generate_3d_model jobs (their uuid would otherwise be read as video). Optional otherwise: other uuids are detected as video, plain numbers default to image.
  • job_id · string · optionnel
    Optional job ID to check — a number for image/music/sound-effect/depth-map jobs, a uuid for video and 3D-model jobs. If omitted, returns all active generation jobs (images, videos, music, and sound effects).

  Exemple d'appel

  {"name": "check_generation_status", "arguments": {"type": "image", "job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_social_post≈ 943 tokens

  Publish a post to the user's PUBLIC BudgetPixel community feed — visible to everyone and labeled "via MCP". ONLY use this when the user EXPLICITLY asks to post/share/publish; never post proactively. Costs 10 credits per post (anti-spam, charged on publish — same as the developer API) with an hourly posting cap. media: 1–6 images, or 1 video + up to 3 images, or exactly 1 audio track — pass the URLs you got from generations (check_generation_status links) or upload_media, or any public URL/base64. Images can carry optional model/prompt generation info. Audio posts accept song_name, genre (a fixed list — see the enum), lyrics, AND cover_image (cover art goes in its own field, never as a second media item). To enter the post in one of the user's clan themes, pass theme_id (call list_my_themes to find it). Posts are All Rights Reserved by default; pass license ("cc-by" or "cc0") ONLY when the user explicitly asks for a Creative Commons license — it is permanent and cannot be changed after publishing. Returns the public post URL — share it with the user. Posts are moderated after publish (NSFW/spam rating affects feed visibility; the charge is not refunded for hidden posts).

  Paramètres, retour & exemple (8)

  Paramètres

  • genre · string · optionnel · Pop | Rock | Hip-Hop & Rap | R&B & Soul | Electronic & Dance | Lo-fi & Chill | Ambient | Jazz
    Audio posts only: the track's genre — EXACTLY one of these values. Omit to have it classified automatically after publishing.
  • media · array · requis
    1–6 media items. Rules: 1–6 images, OR 1 video plus up to 3 images, OR exactly 1 audio track (audio can't mix).
  • lyrics · string · optionnel
    Audio posts only: lyrics to show with the track.
  • content · string · optionnel
    The post's text/caption (optional — media-only posts are fine).
  • license · string · optionnel · arr | cc-by | cc0
    Optional content license: "arr" (All Rights Reserved — the default), "cc-by" (CC BY 4.0) or "cc0" (CC0, public domain). OMIT unless the user EXPLICITLY asks for a Creative Commons license — never choose one on their behalf. Permanent: the license cannot be changed after publishing.
  • theme_id · integer · optionnel
    Optional: enter the post in a live clan theme — the id from list_my_themes (or the number in a budgetpixel.com/themes/<id> link). Works with any media type; posting to a theme of a clan the user hasn't joined joins them to it, like on the site.
  • song_name · string · optionnel
    Audio posts only: the track's display name.
  • cover_image · string · optionnel
    Audio posts only: cover art — an image URL (generation link / upload_media URL), data URI, or base64 (max 15MB). Goes in THIS field, never as a media item.

  Exemple d'appel

  {"name": "create_social_post", "arguments": {"media": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_3d_model≈ 667 tokens

  Turn one picture into a textured 3D model (image-to-3D). Always returns a GLB; meshy-7.1 also offers FBX, USDZ (iPhone AR) and STL (3D printing). Pick the model by job: tripo-h3.1 (default) is the most faithful reconstruction — including cartoons and stylized art — with PBR materials, ~4 min, 400 credits; meshy-7.1 makes lighter ~30K-triangle models in more formats and supports rigging + animation for humanoid characters, ~2 min, 1600 credits. Best input is one subject on a plain background. Submits an async job and returns a job_id — 3D models take 2-5 minutes, so poll check_generation_status with this job_id and type "3d" every 15-30 seconds; when done it returns the thumbnail inline plus download links (GLB/FBX/USDZ/STL). Files are kept about 24 hours, so download them promptly (save_to_assets does not take 3D models). Charged on success only.

  Paramètres, retour & exemple (7)

  Paramètres

  • image · string · requis
    The picture to turn into a 3D model — a public image URL, a data URI, or raw base64 (upload a local file with upload_media first). Best results: one subject, centered, on a plain background.
  • model · string · optionnel · tripo-h3.1 | meshy-7.1
    3D model id. Omit for the default (tripo-h3.1 — most faithful reconstruction, including cartoons and stylized art, PBR materials, GLB only, ~4 min, 400 credits). meshy-7.1: lighter ~30K-triangle models, more output formats (GLB, FBX, USDZ for iPhone AR, STL for 3D printing), rigging + animation for humanoid characters, ~2 min, 1600 credits. Call list_models for exact prices.
  • rigging · boolean · optionnel
    meshy-7.1 only: add a humanoid skeleton rig (characters/figures only). +270 credits. Ignored on tripo-h3.1.
  • texture · boolean · optionnel
    Generate PBR textures (default true). false makes an untextured mesh for less (tripo-h3.1 270, meshy-7.1 1080).
  • animation · boolean · optionnel
    meshy-7.1 only, needs rigging true: add walk/run animation clips. +160 credits. Ignored on tripo-h3.1.
  • texture_quality · string · optionnel · standard | detailed
    tripo-h3.1 only, when texture is true: standard (default) or detailed (sharper textures, 540 credits instead of 400). Ignored on meshy-7.1.
  • detailed_geometry · boolean · optionnel
    tripo-h3.1 only: finer mesh detail, +270 credits. Ignored on meshy-7.1.

  Exemple d'appel

  {"name": "generate_3d_model", "arguments": {"image": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_depth_map≈ 1077 tokens

  Use this to turn a video into a depth map video (Video Depth Anything, on BudgetPixel's own GPUs): a steady, flicker-free video where near is white and far is black, at the input's size (up to 1080p) and frame rate (up to 30 fps). Use it as a depth / structure / motion reference or control video for video models — grayscale (the default colormap) is what they take as a depth reference; turbo, inferno, magma and viridis colour it for viewing only. Priced per second of the INPUT video, rounded up to whole seconds, 5-second minimum, by model size: small 20 / base 30 / large 40 credits per second (a 5-second clip or shorter costs 100 / 150 / 200, a 10-second clip 200 / 300 / 400). The resolution does not change the price. small is fastest; base adds edge detail; large draws the finest detail (hair, thin poles, distant people) and is the steadiest. Input: a video URL (pass one from upload_media for local files), up to 30 seconds and 50MB. Options: size (default small), colormap (default grayscale), resolution (default auto = the input's size, never upscaled), keep_audio (copy the input's audio), side_by_side (input on the left, depth map on the right), face_mesh (no extra charge: draws each face's mesh so a video model keeps lip, eye and head movement; set it when people talk or emote), max_faces (1-4, default 4), include_face_landmarks (no extra charge: also returns a face landmarks JSON link). The price is held when the job starts and charged on success only; a failed job is never charged. Jobs take about 1-2 minutes: the tool returns a job_id — poll check_generation_status with that job_id and type "depth" every 15-30 seconds until it returns the finished depth video, then tell the user. The depth video is also saved to the user's BudgetPixel library.

  Paramètres, retour & exemple (9)

  Paramètres

  • size · string · optionnel · small | base | large
    Model size, which sets the price per second of input video: small 20 (default, fastest), base 30 (adds edge detail), large 40 (finest detail — hair, thin poles, distant people — and the steadiest).
  • video · string · requis
    The video to turn into a depth map: an http(s) URL (a generated video's URL, or one from upload_media for local files). Up to 30 seconds, ≤50MB. Required.
  • colormap · string · optionnel · grayscale | turbo | inferno | magma | viridis
    grayscale (default; near = white, far = black) is what video models take as a depth reference. turbo, inferno, magma and viridis colour the depth map for viewing — not for use as a reference.
  • face_mesh · boolean · optionnel
    Draw a mesh over each face (eyes, brows and lips in colour) so a video model given the depth map keeps lip, eye and head movement: use it when people talk or show expressions. Faces are found automatically; a face turned to full profile gets no mesh. No extra charge (default false).
  • max_faces · integer · optionnel
    Most faces tracked at once, 1-4, largest first (default 4). Applies to face_mesh and include_face_landmarks.
  • keep_audio · boolean · optionnel
    Copy the input's audio into the depth video (default false).
  • resolution · string · optionnel · auto | 360p | 480p | 720p | 1080p
    The output's short side: auto (default) keeps the input's size, up to 1080p. It never upscales, and the price is the same at every resolution.
  • side_by_side · boolean · optionnel
    Put the input on the left and the depth map on the right, twice the width (default false).
  • include_face_landmarks · boolean · optionnel
    Also return a link to a JSON file of per-frame face landmarks (478 3D points), 52 expression scores and head pose for each face, for animation or analysis. Works with or without face_mesh. No extra charge (default false).

  Exemple d'appel

  {"name": "generate_depth_map", "arguments": {"video": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_image≈ 1406 tokens

  Use this to create or edit an AI image. Text-to-image from a prompt, OR image-to-image / editing / multi-reference by passing input_images (URLs, data URIs, or base64) — e.g. edit or restyle an image the user just generated by passing its URL. Input support is per-model: some take 1 image, some several, some none (check each model's max_input_images via list_models). Submits an async job and returns a job_id — then call check_generation_status to poll (usually ready in seconds); when complete it returns the finished image inline for you to display. Each call starts a new job that spends credits from the user's BudgetPixel balance (failed jobs aren't charged). Default model: seedream-5.0-pro; call list_models to see every available model with prices and input limits. Write @handle in the prompt to cast a character (list_characters), e.g. a free BudgetPixel AI influencer like @barry.

  Paramètres, retour & exemple (13)

  Paramètres

  • seed · integer · optionnel
    Seed for reproducible generation
  • model · string · optionnel
    AI model id. Omit for the default (seedream-5.0-pro — strong identity preservation, good for edits, up to 9 reference images). For fast, low-cost drafts pick flux-3-image-klein (FLUX 3 Klein: 12 credits at 1K, up to 10 free references, images in seconds) or seedream-5.0-flash (flat 25 credits, free references). By job: gpt-image-2.5-sunburst (precise edits), gpt-image-2.5-flare (fast everyday generation), seedream-4.5 (photorealism), gpt-image-2 (text in images), nano-banana-2.1 (fast, sharp text in images, up to 9 free references; optional paid search grounding), nano-banana-2 (editing), qwen-image-3.0 (all-rounder), flux-3-image (FLUX 3: up to 10 free references, optional web grounding; priced by size, 55 credits at 768px up to 790 at 4K). Call list_models for the full catalog with prices and input limits.
  • prompt · string · requis
    Text prompt describing the image to generate
  • quality · string · optionnel
    Optional rendering quality for models that support it (gpt-image-2: low/medium/high; gpt-image-2.5-sunburst and gpt-image-2.5-flare: low/medium/high/xhigh/max; grok-imagine-image-2: low/medium — no high tier). Higher costs more. On grok-imagine-image-2 quality x resolution sets the price (low 1K=50, low 2K=80, medium 1K=80, medium 2K=100 credits). Omit for default.
  • grounding · boolean · optionnel
    Optional, flux-3-image only: let the model research the prompt with web and image search before rendering. On by default and free. Set false for faster, self-contained generation. Omit for the default.
  • background · string · optionnel · opaque | transparent
    Optional output background for models that support it (seedream-5.0-flash, seedream-5.0-pro — see list_models). "transparent" keeps a transparent background when EDITING: pass exactly one input image, a PNG that already has transparent pixels (a cutout, sticker or logo), and you get back a PNG with transparency. It cannot make a transparent image from text alone. Omit (or "opaque") for a normal image.
  • num_images · integer · optionnel
    Number of images to generate (1-4)
  • resolution · string · optionnel
    Optional output size (per-model options, e.g. seedream-5.0-pro & seedream-5.0-flash: 1K/2K; gpt-image-2 & nano-banana-2: up to 4K; nano-banana-2.1: 1K/2K/4K; flux-3-image and flux-3-image-klein: 768px/1K/1.5K/2K/4K — see list_models for what each size costs). Omit for the model default. Larger costs more, sometimes far more: flux-3-image is 55/65/90/130/790 credits per image at 768px/1K/1.5K/2K/4K (flux-3-image-klein 11/12/15/19/48), so confirm with the user before choosing 4K.
  • aspect_ratio · string · optionnel · 1:1 | 4:3 | 3:4 | 16:9 | 9:16 | 3:2 | 2:3 | 21:9
    Aspect ratio of the generated image. Omit for the default: 1:1 — except an edit with flux-3-image, flux-3-image-klein or nano-banana-2.1, which keeps the first input image's shape unless you set a ratio here.
  • image_search · boolean · optionnel
    Optional, nano-banana-2.1 only: let the model look up web images as visual reference before rendering (what a real place, product or landmark looks like). Off by default. It runs a Google Search too, so it costs 20 credits per image in total, with or without google_search (list_models shows the current price). Tell the user it adds to the cost.
  • input_images · array · optionnel
    Optional input image(s) for image-to-image / editing / multi-reference — each a public image URL, a data URI, or raw base64. Per-model support: some models take 1, some several, some none (see max_input_images in list_models). Omit for text-to-image. To edit an image the user just generated, pass its URL here.
  • google_search · boolean · optionnel
    Optional, nano-banana-2.1 only: ground the image in live Google Search results (weather, scores, recent events, current facts). Off by default. Costs extra: 10 credits per image (list_models shows the current price). Turn it on only when the request needs current, real-world information, and tell the user it adds to the cost.
  • negative_prompt · string · optionnel
    What to avoid in the generated image

  Exemple d'appel

  {"name": "generate_image", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_music≈ 1007 tokens

  Use this to create an AI music track (full songs with vocals, or instrumentals). Three models: music-3.0 (default, 200 credits — songs from a prompt and/or lyrics, lyrics optimizer on by default so a prompt alone works), mureka-v9 (60 credits — sings the user's EXACT lyrics verbatim, or instrumental/BGM), and lyria-3 (100 credits — high-fidelity from a rich prompt, can condition on up to 10 reference images), and sonilo-music (instrumental/background music of an EXACT length via duration, 5–360 s — priced PER SECOND at 4 credits/s with a 10-second minimum, no vocals). VIDEO-TO-MUSIC: pass a `video` URL (upload_media first for local files) and sonilo-video-music composes a licensed soundtrack for the clip's content, pacing and mood — priced per second of the video's measured length (15 credits/s, 10 s minimum, ≤360 s). Flat price per track (per second for the Sonilo models), charged on success only; each call starts a new paid job. Submits an async job and returns a numeric job_id — music takes a minute or three: poll check_generation_status with the job_id AND type "music" every 15–30 seconds, then share the finished track's listen/download link with the user (chat can't embed audio players).

  Paramètres, retour & exemple (10)

  Paramètres

  • model · string · optionnel
    Music model id. Omit for the default (music-3.0 — latest MiniMax, all-purpose songs, 200 credits; passing a video auto-selects sonilo-video-music). Alternatives: music-2.6 (previous generation, same price), mureka-v9 (sings exact lyrics, cheapest at 60), lyria-3 (high-fidelity, image conditioning, 100), sonilo-music (instrumental/background music of an exact length, priced per second — pass duration). Call list_models for details.
  • video · string · optionnel
    Video-to-music: URL of a video (≤360 s, ≤30 MB for public URLs) to compose a licensed soundtrack FOR — the music follows the clip's content, pacing and mood, and matches its length. Must be a URL — upload local files with upload_media first. Uses sonilo-video-music: 15 credits per second of the video's measured duration (10-second minimum). prompt becomes optional direction (genre/mood/instrumentation); no lyrics or duration.
  • format · string · optionnel
    music-2.6/music-3.0 only: output audio format, wav (default) or mp3.
  • images · array · optionnel
    lyria-3 only: up to 10 reference images to condition the mood — each a URL, data URI, or raw base64 (upload local files with upload_media).
  • lyrics · string · optionnel
    Lyrics to sing. mureka-v9 sings them VERBATIM ([verse]/[chorus] tags supported); music-2.6/music-3.0 polish them unless lyrics_optimizer is false; lyria-3 treats them as optional guidance.
  • prompt · string · optionnel
    Style/mood description of the track. Required for lyria-3 (10–2000 chars) and for instrumental tracks; optional on music-2.6/music-3.0 when lyrics are given.
  • duration · integer · optionnel
    sonilo-music only: track length in seconds (5–360, default 30). Billed per second with a 10-second minimum (4 credits/s → 30 s = 120 credits). Other music models ignore length (sonilo-video-music sizes the music to the video).
  • instrumental · boolean · optionnel
    Generate an instrumental track (no vocals). music-2.6/music-3.0 and mureka-v9 (mureka requires a prompt in this mode).
  • vocal_gender · string · optionnel · auto | female | male
    mureka-v9 only: preferred vocal gender for songs (default auto).
  • lyrics_optimizer · boolean · optionnel
    music-2.6/music-3.0 only. Write/polish lyrics from the prompt — DEFAULT TRUE (matches web/API). Set false to sing the provided lyrics as-is.

  Exemple d'appel

  {"name": "generate_music", "arguments": {"model": "texte", "video": "texte", "format": "texte", "images": [], "lyrics": "texte", "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_sound_effect≈ 663 tokens

  Use this to create sound effects (NOT music). TEXT mode: describe the sound — Foley, ambience, UI sounds, whooshes/transitions, impacts, action sounds — with sonilo-sfx: 1–180 seconds, mp3 or wav, PRICED PER SECOND of the requested duration (5 credits/s, 3-second minimum → 5 s = 25, 10 s = 50, 30 s = 150 credits). VIDEO mode: pass a video URL (upload local files with upload_media first) to get frame-accurate effects synced to the clip's visible events with sonilo-video-sfx — billed per second of the VIDEO's measured length (15 credits/s, 3-second minimum, up to 360 s) and returns both the SFX track and the video with the effects mixed in. Each call starts a new paid job, charged on success only. Keep text clips as short as the sound needs and confirm cost for long videos. Submits an async job and returns a numeric job_id — text clips finish within ~15 seconds, video jobs can take a few minutes: poll check_generation_status with the job_id AND type "sound_effect" every 5–15 seconds, then share the finished link(s) with the user (chat can't embed players). For songs or background music use generate_music instead.

  Paramètres, retour & exemple (5)

  Paramètres

  • model · string · optionnel
    Sound-effect model id. Omit for the default (sonilo-sfx for text; sonilo-video-sfx is selected automatically when video is given). Call list_models for details.
  • video · string · optionnel
    Optional INPUT VIDEO URL to sync the effects to (frame-accurate Foley/ambience/impacts for the clip's visible events). Must be a URL — upload local files with upload_media first; public URLs OK (≤30 MB, ≤360 s). Uses sonilo-video-sfx: 15 credits per second of the video (3-second minimum); returns the SFX track AND the video with the effects mixed in. prompt becomes optional direction.
  • format · string · optionnel · mp3 | wav
    Output audio format: mp3 (default, small) or wav (lossless, for editing).
  • prompt · string · optionnel
    Description of the sound effect — Foley, ambience, UI sounds, transitions, impacts, action (e.g. 'heavy rain on a tin roof with distant thunder'). Up to 1000 characters.
  • duration · integer · optionnel
    Text mode: length of the clip in seconds (1–180, default 10). Billed per second with a 3-second minimum — 10 s = 50 credits on the default model. Ignored when a video is given.

  Exemple d'appel

  {"name": "generate_sound_effect", "arguments": {"model": "texte", "video": "texte", "format": "mp3", "prompt": "texte", "duration": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_video≈ 1558 tokens

  Use this to create or edit an AI video. Text-to-video from a prompt; image-to-video by passing image (start frame, + optional end_image); reference-to-video by passing reference_images; or video-to-video editing by passing video (an input video URL — upload local files with upload_media first). IMPORTANT — cost: video is priced per SECOND and by resolution (default model seedance-2.5: 480p=150, 720p=330, 1080p=750 credits/sec, plus 80/160/375 per second of reference-video INPUT), so e.g. 5s at 720p ≈ 1,650 credits and 5s at 1080p ≈ 3,750; confirm with the user before expensive combos (long durations or many reference clips). Each call starts a new paid job, charged on success only. Submits an async job and returns a job_id (uuid) — video takes MINUTES: poll check_generation_status every 15–30 seconds until it returns the finished video link, then share that link with the user. Default model: seedance-2.5; call list_models for available video models and prices. Write @handle in the prompt to cast a character (list_characters), e.g. a free BudgetPixel AI influencer like @barry.

  Paramètres, retour & exemple (15)

  Paramètres

  • mode · string · optionnel · cost | speed | quality
    p-video-2-pro ONLY: generation mode, which sets the price together with resolution — cost (cheapest AND fastest, ~20s for a 5s clip), speed (default), quality (most detail, slowest). Per-second prices per mode are in list_models. Omit for every other model.
  • audio · string · optionnel
    Optional reference audio URL (MP3/WAV/OGG; upload local files with upload_media). Must accompany an image, reference_images, or video input. Not for minimax-h3 / seedance-2.5 / wan-3.0-video(-prime) — use reference_audios there.
  • image · string · optionnel
    Optional START FRAME for image-to-video — a public image URL, a data URI, or raw base64. Can't be combined with reference_images or video.
  • model · string · optionnel
    Video model id. Omit for the default (seedance-2.5 — flagship multimodal: text-to-video, image-to-video, reference images/videos/audio; pass a clip as reference_videos to edit/extend; 480p/720p/1080p, up to 30s). wan-3.0-video is the Alibaba all-in-one alternative — same modes, up to 30s, and ALL input media free (480p 60 / 720p 120 / 1080p 240 credits/sec output-only; wan-3.0-video-prime is the same model generating much faster at 85/170/340). For cheaper drafts pick seedance-2.0-mini (480p 60 / 720p 120 credits/sec). Call list_models for per-resolution prices.
  • video · string · optionnel
    Optional INPUT VIDEO for video-to-video editing (2-15s) — must be a URL (upload local files with upload_media first). Can't be combined with image/end_image. On the seedance-2.0 family the INPUT seconds are billed at half the output per-second rate on top of the output. On minimax-h3-max the video is EXTENDED instead (1.6-60s source; length_seconds = new footage appended; source billed 170 credits/sec, first 15s). On flux-3-video it is EXTENDED too (1s-2min source, free; length_seconds = 5-15s of new footage at the extend rate; the result is the source followed by the new footage).
  • prompt · string · requis
    Text prompt describing the video to generate (or the edit to apply, when passing an input video)
  • end_image · string · optionnel
    Optional END FRAME used together with image (the start frame) — the video interpolates between the two.
  • resolution · string · optionnel
    Output resolution — PRICING VARIES A LOT (seedance-2.5: 480p=150, 720p=330, 1080p=750 credits per SECOND, default 720p; seedance-2.0: 1080p=550/4k=1250). Prefer 480p unless asked.
  • aspect_ratio · string · optionnel
    Aspect ratio (seedance-2.5: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 — default 16:9). On minimax-h3 it applies to TEXT-TO-VIDEO only. On seedance-2.5 it applies to t2v AND jobs with reference images/audio; a start/end frame or a reference VIDEO forces adaptive (output follows the input's frame). On wan-3.0-video (and -prime) it is honored in EVERY mode (even with a first frame or reference media) and also accepts 'adaptive' (its default — the model picks a suitable ratio from the inputs).
  • generate_audio · boolean · optionnel
    Whether the model should generate audio with the video (no price impact on seedance-2.5/2.0 or flux-3-video).
  • negative_prompt · string · optionnel
    What to avoid in the generated video
  • duration_seconds · integer · optionnel
    Video length in seconds (seedance-2.5: 4–30, default 5; seedance-2.0: 4–15). Cost scales linearly.
  • reference_audios · array · optionnel
    minimax-h3 / minimax-h3-max / seedance-2.5 / wan-3.0-video(-prime) only: reference AUDIO clip URLs (WAV/MP3; h3 ≤3/15s combined, 2.5 ≤5/30s combined, wan-3.0(-prime) ≤5/15s combined; free; upload local files with upload_media). Can't be combined with image/end_image.
  • reference_images · array · optionnel
    Optional reference images guiding the video (subject consistency) — each a URL, data URI, or base64. seedance-2.5: up to 15; wan-3.0-video / wan-3.0-video-prime: up to 10 (free); seedance-2.0: up to 9 alone, 6 alongside an input video. Can't be combined with image/end_image.
  • reference_videos · array · optionnel
    minimax-h3 / minimax-h3-max / seedance-2.5 / wan-3.0-video(-prime) only: reference VIDEO clip URLs guiding motion/identity — on seedance-2.5 and wan-3.0-video(-prime) also how you edit/extend a clip (h3: ≤3, 15s combined; 2.5: ≤5, 30s combined; wan-3.0(-prime): ≤5, 15s combined, and input + output ≤ 30s; upload local files with upload_media). h3 and 2.5 bill INPUT seconds on top of the output (h3 160/s; 2.5 80/160/375 per s at 480p/720p/1080p); wan-3.0-video(-prime) input is FREE. Can't be combined with image/end_image.

  Exemple d'appel

  {"name": "generate_video", "arguments": {"prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_character≈ 226 tokens

  Use this to learn one character before casting it or using it elsewhere: its look word for word, personality, speaking style, backstory, directing notes, signature details and consistency rules, every picture with a download link (full size for the BudgetPixel influencers and the user's own characters, so they can be used with other tools too), the models a mention works on, and the terms for using an influencer. Use the profile to write prompts, captions and scripts in the character's own voice. Free.

  Paramètres, retour & exemple (1)

  Paramètres

  • handle · string · requis
    The character's handle, with or without the @ (e.g. "barry"), from list_characters.

  Exemple d'appel

  {"name": "get_character", "arguments": {"handle": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_credit_balance≈ 105 tokens

  Use this when the user asks about their remaining credits, subscription plan, or usage. Returns monthly credit balance, extra credits, total available, and plan name.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_credit_balance", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_generation_history≈ 368 tokens

  Get the user's recent generations made through this connector or the developer API — images by default, or pass type "video", "music", or "sound_effect". Outputs are kept for about 24 hours (they are never saved to the user's asset storage unless save_to_assets is called), so rows older than that show as expired with no link. Returns prompts, models, status, and result links: image URLs (reusable as input_images on generate_image to edit/restyle one — e.g. "make the third one wintery"), video watch links, or music / sound-effect listen links (also reusable as create_social_post media). Every row's job_id works with check_generation_status (music and sound effects also need their type) and with save_to_assets. Generations the user made on the BudgetPixel website are in their gallery, not here.

  Paramètres, retour & exemple (3)

  Paramètres

  • type · string · optionnel · image | video | music | sound_effect
    Which history to fetch: image (default), video, music, or sound_effect.
  • limit · integer · optionnel
    Number of recent generations to return (1-50, default 10)
  • offset · integer · optionnel
    Offset for pagination (default 0)

  Exemple d'appel

  {"name": "get_generation_history", "arguments": {"type": "image", "limit": 1, "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_characters≈ 339 tokens

  Use this to see the characters the user can cast in images and videos: the free BudgetPixel AI influencers (memorable personas with a consistent face, like @barry, @rosa or @fifi, free for every user) plus the user's own and collected characters. To cast one, write its @handle in the prompt of generate_image or generate_video (e.g. "@barry orders coffee like he owns the cafe") on a model that takes characters. q filters by words (e.g. "fitness"); source narrows to official, mine or collected. For one character's full profile and pictures call get_character; to pick influencers for a brief call recommend_influencers. Free.

  Paramètres, retour & exemple (3)

  Paramètres

  • q · string · optionnel
    Optional words that must all appear in the character's name, look or profile, e.g. "fitness" or "beauty".
  • limit · integer · optionnel
    Optional: at most this many (default 100).
  • source · string · optionnel · all | official | mine | collected
    Optional: official (the BudgetPixel AI influencers), mine (the user's own), collected, or all (default).

  Exemple d'appel

  {"name": "list_characters", "arguments": {"q": "texte", "limit": 1, "source": "all"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_models≈ 270 tokens

  List the AI image, video, music, sound-effect, and 3D models available on BudgetPixel, plus the depth-map tool's sizes, with standard credit prices and capabilities. Featured models come first with a one-line role hint (when to pick each). Image models that charge by output size list every size's price (the size you pass as resolution sets the price). Video models are priced per SECOND by resolution; music models are flat per track; sound effects are per second with a 3-second minimum; 3D models are priced per job (base price plus named options); depth maps (generate_depth_map) are priced per second of the input video by model size (small / base / large), 5-second minimum. Prices shown are standard rates in credits. Video resolutions delivered as H.265 (HEVC) instead of H.264 are marked, because some browsers cannot play H.265.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_models", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_my_themes≈ 163 tokens

  List the live clan themes the user can post to — themes of the clans they own, moderate, or have joined (each with the user's role, the theme's brief, and when entries close). Use it when the user wants to post into a theme / enter a theme / share to their clan, then pass the chosen theme's id as create_social_post's theme_id. Free and read-only; themes that haven't started or have ended are not listed.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_my_themes", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recommend_influencers≈ 299 tokens

  Use this when the user wants an AI influencer or a character for a product, brand, campaign, ad or post and hasn't picked one. Pass the brief (what it is, for whom, where it will be posted) and get the BudgetPixel AI influencers who fit it best, each with why, a content idea and a ready-to-use prompt that starts with their @handle (pass it to generate_image or generate_video). include_mine also considers the user's own characters. Free.

  Paramètres, retour & exemple (3)

  Paramètres

  • brief · string · requis
    What the content is, for whom and where it will be posted, e.g. "a 10-second TikTok ad for a protein shake aimed at gym beginners". Up to 1,000 characters.
  • count · integer · optionnel
    How many to recommend (1-5, default 3).
  • include_mine · boolean · optionnel
    Also consider the user's own and collected characters (default false: BudgetPixel influencers only).

  Exemple d'appel

  {"name": "recommend_influencers", "arguments": {"brief": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• save_to_assets≈ 336 tokens

  Keep a generation permanently. Outputs made through this connector expire about 24 hours after generation and are NOT stored in the user's BudgetPixel assets by default. Call this when the user wants to keep, reuse later, or find a result in their gallery / workshops — it copies the output into their assets (this counts against their storage like a website generation). Pass the job_id (and type for video / music / sound_effect). Safe to call twice: an already-saved job just reports already_saved.

  Paramètres, retour & exemple (3)

  Paramètres

  • type · string · optionnel · image | video | music | sound_effect
    What kind of generation job_id is: image (default), video, music, or sound_effect.
  • job_id · string · requis
    The generation to keep — the job_id from generate_image / generate_music / generate_sound_effect / check_generation_status / get_generation_history (numeric), or the video job uuid from generate_video.
  • folder_id · integer · optionnel
    Optional asset folder id to save into (defaults to Uncategorized).

  Exemple d'appel

  {"name": "save_to_assets", "arguments": {"job_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_stock_audio≈ 784 tokens

  Use this when the user needs an existing sound effect or a piece of background music — for a video, podcast, stream, game, app or presentation — rather than a newly generated one. Searches BudgetPixel's free audio library, licensed CC BY 4.0 for commercial use, every item listened to and scored before listing. kind "sound_effect": whooshes, impacts, UI sounds, Foley, ambiences, animals, vehicles (a fraction of a second to about 6 s). kind "music": instrumental background tracks such as lofi, corporate, cinematic, acoustic (up to about a minute). Costs 10 credits per search, charged even when nothing matches. Try it before generate_sound_effect or generate_music: a search is cheaper and instant. Write the query as a few plain words naming the sound ("door creak", "soft notification chime", "lofi study beat"), not a generation prompt: every word counts, and a word the library does not have counts as a miss. It never generates: if nothing fits, say so. LICENCE: wherever a result is used, include its credit line exactly as returned (the `attribution` text; `attribution_html` for web pages).

  Paramètres, retour & exemple (8)

  Paramètres

  • kind · string · requis · sound_effect | music
    Which library: "sound_effect" (whooshes, impacts, UI sounds, Foley, ambiences) or "music" (instrumental background tracks).
  • sort · string · optionnel · popular | newest | top
    popular (default — best matches first when there is a query), newest, or top (highest rated).
  • limit · integer · optionnel
    How many results to return (default 10, max 20). The price is the same for any limit.
  • query · string · optionnel
    The sound, in a few plain words — e.g. "door creak", "soft notification chime", "rain on a tin roof"; for music the genre, mood or use — "lofi study", "upbeat corporate", "dark true crime documentary". Max 200 characters. Name the sound itself; leave out lengths and production notes. Optional only when browsing a sound-effect category.
  • offset · integer · optionnel
    For the next page: the previous offset plus the number returned. Each page is a new 10-credit search.
  • category · string · optionnel · transition | impact | stinger | ui | game | human | animals | vehicles
    Optional category filter. Sound effects only; music has no categories.
  • max_duration · number · optionnel
    Optional: longest result, in seconds (e.g. 1 for one-shot sound effects).
  • min_duration · number · optionnel
    Optional: shortest result, in seconds (e.g. 30 for a music bed of at least half a minute).

  Exemple d'appel

  {"name": "search_stock_audio", "arguments": {"kind": "sound_effect"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_stock_images≈ 748 tokens

  Use this when the user needs an existing stock photo, illustration, background, wallpaper or texture — for a website, slide, blog post, app, video or design — rather than a newly generated image. Searches BudgetPixel's stock image library: AI-generated images, each reviewed before listing (no real people, logos or text), licensed CC BY 4.0 for commercial use. Set transparent to true for cut-outs only: PNG files with a transparent background, for stickers, overlays and compositing. Costs 10 credits per search, charged even when nothing matches, so write one specific query rather than many vague ones. It never generates: if nothing fits, say so. LICENCE: wherever an image is used, include its credit line exactly as returned (the `attribution` text; `attribution_html` for web pages). Download from the returned URLs rather than hotlinking them in production.

  Paramètres, retour & exemple (9)

  Paramètres

  • sort · string · optionnel · popular | newest | top
    popular (default — best matches first when there is a query), newest, or top (highest rated).
  • type · string · optionnel · photo | illustration
    Optional: photos only, or illustrations (including 3D and painted art) only.
  • color · string · optionnel · red | orange | yellow | green | turquoise | blue | purple | pink
    Optional dominant-colour filter.
  • limit · integer · optionnel
    How many results to return (default 10, max 20). The price is the same for any limit.
  • query · string · optionnel
    What the image should show, in plain words — e.g. "misty pine forest at sunrise", "latte art on a wooden table", "abstract purple gradient background". Max 200 characters. Optional only when browsing a category.
  • offset · integer · optionnel
    For the next page: the previous offset plus the number returned. Each page is a new 10-credit search.
  • category · string · optionnel · nature | backgrounds | wallpapers | textures | animals | food | travel | transportation
    Optional category filter.
  • orientation · string · optionnel · landscape | portrait | square
    Optional shape filter: landscape for headers and slides, portrait for phone wallpapers and stories.
  • transparent · boolean · optionnel
    Optional: true returns cut-outs only — PNG files with a transparent background, for stickers, overlays and compositing. Omit for every image.

  Exemple d'appel

  {"name": "search_stock_images", "arguments": {"sort": "popular", "type": "photo", "color": "red", "limit": 1, "query": "texte", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• upload_media≈ 258 tokens

  Upload a local image, video, or audio file to BudgetPixel and get back a short-lived URL (valid ~24h) to use as a generation input: pass it as an input_images value on generate_image, or as image / end_image / reference_images / video / audio on generate_video. Use this when the user has a LOCAL file: read the file and pass its base64 as 'file'. Not charged; max 50MB. Video/audio inputs REQUIRE this (generate_video takes them by URL only). If you already have a public URL, pass it straight to the generate tool instead.

  Paramètres, retour & exemple (1)

  Paramètres

  • file · string · requis
    The file to upload, as raw base64 or a data URI (data:image/png;base64,...). Read the local file and pass its base64 here. Max 50MB. Images: PNG/JPEG/WebP/GIF · Video: MP4/WebM · Audio: MP3/WAV/OGG.

  Exemple d'appel

  {"name": "upload_media", "arguments": {"file": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• upscale_image≈ 520 tokens

  Use this to upscale an image to a higher resolution. Default model p-image-upscale (Pruna AI) returns results in seconds and is priced by the target resolution: 4 MP = 10, 8 MP = 15, 16 MP = 30, 32 MP = 60 credits. Alternative clarity-upscaler does creative detail enhancement (steer with prompt/creativity) at a flat 30 credits and takes ~60 seconds. Pass the image as a URL (a generated image's URL, or upload_media for local files), a data URI, or base64. Charged on success only. The tool waits for the result and returns the upscaled image's URL — share it with the user. Unlike generations, the upscaled image is also saved to the user's BudgetPixel library.

  Paramètres, retour & exemple (7)

  Paramètres

  • image · string · requis
    The image to upscale: an http(s) URL (a generated image's URL, or one from upload_media for local files), a data URI, or raw base64. Max ~20MB.
  • model · string · optionnel
    Upscale model: p-image-upscale (default — Pruna AI, results in seconds, priced by target resolution 4/8/16/32 MP = 10/15/30/60 credits) or clarity-upscaler (creative detail enhancement, flat 30 credits, ~60s).
  • prompt · string · optionnel
    clarity-upscaler only: optional guiding prompt describing the image content.
  • target · integer · optionnel · 4 | 8 | 16 | 32
    p-image-upscale only: target output resolution in megapixels (sets the price: 4=10, 8=15, 16=30, 32=60 credits; default 4).
  • creativity · number · optionnel
    clarity-upscaler only: how much new detail the model may invent (0.3-0.9, default 0.35).
  • enhance_details · boolean · optionnel
    p-image-upscale only: enhance textures and fine detail (may increase contrast).
  • enhance_realism · boolean · optionnel
    p-image-upscale only: improve realism — recommended for AI-generated images.

  Exemple d'appel

  {"name": "upscale_image", "arguments": {"image": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• upscale_video≈ 772 tokens

  Use this to upscale a video, with one of two models. Topaz (model topazlabs-video-upscale, the default): 1080p or 4K at 30 or 60 fps, priced per second of the INPUT video: 1080p = 15 (30fps) / 30 (60fps) credits/s, 4K = 60 / 120 credits/s, so a 10s clip to 1080p30 costs 150 credits; its result is an H.265 (HEVC) 10-bit MP4, which some browsers cannot play (black frame with audio) — tell the user. FLUX 3 Video Upscale (model flux-3-video-upscale): 1.5x to 3x the input frame (input up to 2560x1440), precise (keeps faces and products) or creative (adds fine detail), keeps the frame rate and audio, H.264 output; priced per megapixel-second of OUTPUT: 95 credits precise / 135 creative, so one second of 1080p output is 188 / 267 credits and of 4K 752 / 1068 — it costs far more than Topaz, so state the price and confirm with the user first. Input up to 20 seconds (pass a URL; upload_media for local files). The price is held when the job starts and charged on success only. Jobs take a few MINUTES: the tool returns a job_id — call upscale_video again with just job_id every 30-60 seconds until it returns the finished video URL, then share it. The upscaled video is also saved to the user's BudgetPixel library.

  Paramètres, retour & exemple (8)

  Paramètres

  • mode · string · optionnel · precise | creative
    FLUX only: precise (default) keeps the source as it is (faces, products); creative adds fine detail and costs more (95 vs 135 credits per output megapixel-second).
  • model · string · optionnel · topazlabs-video-upscale | flux-3-video-upscale
    Upscaler: topazlabs-video-upscale (default; 1080p/4K at 30/60 fps, any input size) or flux-3-video-upscale (FLUX 3 super-resolution, 1.5x-3x the input, precise or creative detail; input up to 2560x1440). target_resolution/target_fps are Topaz's; upscale_factor/mode/prompt are FLUX's.
  • video · string · optionnel
    The video to upscale: an http(s) URL (a generated video's URL, or one from upload_media for local files). Up to 20 seconds, ≤50MB. Required unless job_id is set.
  • job_id · integer · optionnel
    A previously returned upscale job id — pass it alone to check progress and fetch the finished video URL.
  • prompt · string · optionnel
    FLUX only, optional: what the clip shows, to steer the detail creative mode adds (up to 1000 characters).
  • target_fps · integer · optionnel · 30 | 60
    Target frame rate (default 30). 60 fps doubles the per-second rate.
  • upscale_factor · number · optionnel · 1.5 | 2 | 2.5 | 3
    FLUX only: how many times larger the output frame is (default 2). 720p at 3 is 4K.
  • target_resolution · string · optionnel · 1080p | 4k
    Target output resolution (default 1080p). 4K costs 4x: 1080p = 15/30 credits per input second (30/60fps), 4K = 60/120.

  Exemple d'appel

  {"name": "upscale_video", "arguments": {"mode": "precise", "model": "topazlabs-video-upscale", "video": "texte", "job_id": 1, "prompt": "texte", "target_fps": 30}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.budgetpixel.com/mcp