About budgetpixel
BudgetPixel MCP Server is a remote media-generation service for MCP clients, creating and upscaling images, video, music, and sound effects. It also supports media uploads, generation status and history checks, and publishing to its community feed.
Key features
- 01Generate and edit images, video, and music
- 02Create sound effects that can sync to video events
- 03Upscale images and video
- 04Upload media and check generation status
- 05Review generation history and remaining credits
Use cases
- 01Create media from text or reference images
- 02Generate sound effects to match video events
- 03Increase image resolution or enhance detail
- 04Track generation jobs and retrieve their results
MCP support
Provides a remote MCP server using OAuth and Streamable HTTP. Its tools handle media generation, upscaling, uploads, job status and history, and community publishing.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.budgetpixel.com/mcpclaude mcp add --transport http com-budgetpixel https://mcp.budgetpixel.com/mcp{"mcpServers":{"com-budgetpixel":{"type":"http","url":"https://mcp.budgetpixel.com/mcp"}}}Open in Cursor{"servers":{"com-budgetpixel":{"type":"http","url":"https://mcp.budgetpixel.com/mcp"}}}Open in VS Code{"mcpServers":{"com-budgetpixel":{"type":"http","url":"https://mcp.budgetpixel.com/mcp"}}}{"mcpServers":{"com-budgetpixel":{"serverUrl":"https://mcp.budgetpixel.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
17| Parameter | Type | Required | Description |
|---|---|---|---|
| seed | integer | No | Seed for reproducible generation |
| model | string | No | 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 | Yes | Text prompt describing the image to generate |
| quality | string | No | 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 | No | 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 | enum | No | 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.opaque | transparent |
| num_images | integer | No | Number of images to generate (1-4) |
| resolution | string | No | 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 | enum | No | 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.1:1 | 4:3 | 3:4 | 16:9 | 9:16 | 3:2 | 2:3 | 21:9 |
| image_search | boolean | No | 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 | No | 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 | No | 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 | No | What to avoid in the generated image |
Details
From the project READMEBudgetPixel 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
claude mcp add budgetpixel --transport http https://mcp.budgetpixel.com/mcp
Cursor, Windsurf, and other config-file clients
{
"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.
Links
- budgetpixel.com/mcp — setup guides
- budgetpixel.com — the platform
- Cursor plugin
Support
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.