com.budgetpixel/mcp (BudgetPixel MCP Server)

BudgetPixel MCP server generates AI images, video, music, and sound effects, and can also upscale them, from any MCP-compatible client. It runs as a remote service, accessed via a Streamable HTTP endpoint with OAuth. The server is intended to be used after connecting and signing in through the client.

🛠️ Key Features

Generate AI images
Generate AI video
Generate AI music
Generate sound effects
Upscale generated media
Exposes an MCP endpoint: https://mcp.budgetpixel.com/mcp
Uses Streamable HTTP and OAuth
Tool count: 12

🚀 Use Cases

Produce AI images, video, music, and sound effects via an MCP client
Upscale existing generated outputs

⚡ Developer Benefits

No install and no API keys to manage
Connect once, then sign in with Google; plan credits and discounts apply automatically
Compatible with Claude Code, Cursor, Windsurf, and other config-file MCP clients

⚠️ Limitations

Requires OAuth-based sign-in (Google) to use plan credits and discounts

BudgetPixel MCP Server

Generate AI images, video, music, and sound effects — and upscale them — from any MCP-compatible client.

BudgetPixel is a remote MCP server. There is nothing to install and no API keys to manage: connect once, sign in with Google, and your BudgetPixel plan credits and discounts apply automatically.

Endpoint: https://mcp.budgetpixel.com/mcp (Streamable HTTP, OAuth)

Setup

Claude Code

bash

claude mcp add budgetpixel --transport http https://mcp.budgetpixel.com/mcp

Cursor, Windsurf, and other config-file clients

json

{
  "mcpServers": {
    "budgetpixel": {
      "type": "http",
      "url": "https://mcp.budgetpixel.com/mcp"
    }
  }
}

Claude, ChatGPT, and other connector UIs — add a custom connector pointing at https://mcp.budgetpixel.com/mcp.

Step-by-step guides for each client: budgetpixel.com/mcp

Tools

Tool	What it does
`generate_image`	Text-to-image, editing, image-to-image, and multi-reference generation
`generate_video`	Text-to-video, image-to-video (start plus optional end frame), reference-to-video, and video-to-video editing
`generate_music`	Full songs from a prompt and/or your own lyrics, or instrumentals
`generate_sound_effect`	Foley, ambience, UI sounds, impacts, and transitions — optionally synced to a video's events
`upscale_image`	Higher resolution in seconds, or creative detail enhancement steered by a prompt
`upscale_video`	1080p or 4K at 30 or 60 fps via Topaz Labs, inputs up to 20 seconds
`list_models`	The live model catalog with prices, role hints, and per-model input limits
`upload_media`	Upload a local file and get a URL to use as a generation input
`check_generation_status`	Poll a running job and collect the finished media
`get_generation_history`	Your recent generations, reusable as inputs
`get_credit_balance`	Remaining plan credits
`create_social_post`	Publish a finished generation to the BudgetPixel community feed

How jobs work

Generation tools return a job id rather than the finished media.

Tool	Job id	Poll with	Typical wait
`generate_image`	numeric	`check_generation_status`	seconds
`generate_video`	uuid	`check_generation_status`	minutes
`generate_music`	numeric	`check_generation_status` with `type: "music"`	a few minutes
`generate_sound_effect`	numeric	`check_generation_status` with `type: "sound_effect"`	~15s text, minutes for video
`upscale_image`	—	returns the result directly	seconds
`upscale_video`	numeric	call `upscale_video` again with just `job_id`	minutes

Music and sound-effect ids are numeric like image ids, so the type argument is required for those two — without it the id is read as an image job.

Local files must go through upload_media first: video and audio inputs on generate_video accept URLs only.

Requirements

A BudgetPixel account. Browsing the model catalog is free; generation, upscaling, uploads, and publishing require any paid plan (Starter, Basic, Premium, Pro or Ultra) — see budgetpixel.com/pricing.

Video is billed per second and by resolution, so confirm cost before long or high-resolution jobs. Failed generations are never charged.

Support

support@budgetpixel.com

License

MIT — see LICENSE.

prompt	string	required	Text prompt describing the image to generate
aspect_ratio	string	optional	Aspect ratio of the generated image
num_images	integer	optional	Number of images to generate (1-4)
model	string	optional	AI model id. Omit for the default (seedream-5.0-pro — premium flagship: top quality, strongest identity preservation, great for edits). For fast & cheap drafts pick flux-2-klein (free on Pro/Ultra plans). Other strong picks: seedream-4.5 (photorealism), gpt-image-2 (text in images), nano-banana-2 (premium editing), qwen-image-3.0 (all-rounder). Call list_models for the full catalog with prices and input limits.
negative_prompt	string	optional	What to avoid in the generated image
seed	integer	optional	Seed for reproducible generation
input_images	array	optional	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.
resolution	string	optional	Optional output size (per-model options, e.g. seedream-5.0-pro: 1K/2K; gpt-image-2 & nano-banana-2: up to 4K — see list_models). Omit for the model default. Larger costs more.
quality	string	optional	Optional rendering quality for models that support it (gpt-image-2: low/medium/high; 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.

prompt	string	required	Text prompt describing the video to generate (or the edit to apply, when passing an input video)
model	string	optional	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.
image	string	optional	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.
end_image	string	optional	Optional END FRAME used together with image (the start frame) — the video interpolates between the two.
reference_images	array	optional	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.
video	string	optional	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.
audio	string	optional	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.
reference_videos	array	optional	minimax-h3 / 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.
reference_audios	array	optional	minimax-h3 / 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.
aspect_ratio	string	optional	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).
resolution	string	optional	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.
duration_seconds	integer	optional	Video length in seconds (seedance-2.5: 4–30, default 5; seedance-2.0: 4–15). Cost scales linearly.
negative_prompt	string	optional	What to avoid in the generated video
generate_audio	boolean	optional	Whether the model should generate audio with the video (no price impact on seedance-2.5/2.0).

prompt	string	optional	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.
lyrics	string	optional	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.
model	string	optional	Music model id. Omit for the default (music-3.0 — latest MiniMax, all-purpose songs, 200 credits). 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.
duration	integer	optional	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.
instrumental	boolean	optional	Generate an instrumental track (no vocals). music-2.6/music-3.0 and mureka-v9 (mureka requires a prompt in this mode).
lyrics_optimizer	boolean	optional	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.
vocal_gender	string	optional	mureka-v9 only: preferred vocal gender for songs (default auto).
format	string	optional	music-2.6/music-3.0 only: output audio format, wav (default) or mp3.
images	array	optional	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).

prompt	string	optional	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	optional	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.
video	string	optional	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	optional	Output audio format: mp3 (default, small) or wav (lossless, for editing).
model	string	optional	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.

image	string	required	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	optional	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).
target	integer	optional	p-image-upscale only: target output resolution in megapixels (sets the price: 4=10, 8=15, 16=30, 32=60 credits; default 4).
enhance_details	boolean	optional	p-image-upscale only: enhance textures and fine detail (may increase contrast).
enhance_realism	boolean	optional	p-image-upscale only: improve realism — recommended for AI-generated images.
prompt	string	optional	clarity-upscaler only: optional guiding prompt describing the image content.
creativity	number	optional	clarity-upscaler only: how much new detail the model may invent (0.3-0.9, default 0.35).

com.budgetpixel/mcp

com.budgetpixel/mcp (BudgetPixel MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

generate_image

generate_video

generate_music

generate_sound_effect

upscale_image

upscale_video

check_generation_status

get_credit_balance

list_models

get_generation_history

upload_media

create_social_post

BudgetPixel MCP Server

Setup

Tools

How jobs work

Requirements

Links

Support

License

Install

Remote endpoint

Related servers

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

content	string	optional	The post's text/caption (optional — media-only posts are fine).
media	array	required	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).
song_name	string	optional	Audio posts only: the track's display name.
genre	string	optional	Audio posts only: the track's genre — EXACTLY one of these values. Omit to have it classified automatically after publishing.
lyrics	string	optional	Audio posts only: lyrics to show with the track.
cover_image	string	optional	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.