Skip to main content
BudgetPixel runs a remote Model Context Protocol server that gives AI agents tools to create with your BudgetPixel account: generate images, video, and music, upload reference files, check pricing and credits, and publish finished work to the BudgetPixel community — all from the chat.
There are no API keys involved: you sign in with Google during the connect flow, and the connector acts as your account. Plan credits, model discounts, and free-generation allowances apply exactly as they do on budgetpixel.com.
Generation, uploads, and posting through MCP require a paid plan — Starter, Basic, Premium, Pro or Ultra — the same plans that include the developer API. Any account, Free included, can connect, browse the model catalog and search the free stock image library (10 credits per search); agents on other plans get a clear upgrade notice when they try to generate.
BudgetPixel exposes two MCP endpoints. This page documents the product server at mcp.budgetpixel.com/mcp — the one that creates images, video, and music with your account. Separately, this documentation site hosts a docs-search server at docs.budgetpixel.com/mcp, giving agents read-only search tools over these docs — useful alongside the API when you want your agent to answer integration questions from the documentation itself.

​
Connect your client

  1. In claude.ai (or the desktop app), open Settings → Connectors and click Add custom connector.
  2. Name it BudgetPixel and paste the server URL:
  3. Click Add → Connect and sign in with Google. Then ask Claude to “generate an image (or video, or song) of … using BudgetPixel”.

​
Available tools

​
Billing

Generations through MCP spend the same credits as the BudgetPixel studio:
  • Your plan’s monthly credits, model discounts, and the Pro/Ultra daily free-models allowance apply automatically.
  • Images are priced per image, video per second by resolution, music per track, and sound effects per second (5 credits/s from text, 15 credits/s of input video; 3-second minimum) — the same published prices as the API. Your agent can check any price up front with list_models.
  • Failed generations are never charged.
  • MCP usage counts toward the monthly spend limit and spend alert you set under Billing — the same guardrails as API keys. When the limit is reached the agent gets a clear “spend limit reached” error; your usage on the website is never blocked.
  • Publishing a community post costs 10 credits (spam prevention — same policy as the API), and posts are limited to 20 per hour. Posts created this way carry a “via MCP” label for transparency.
  • A stock image search costs 10 credits, charged even when nothing matches.

​
Try asking

Once connected, prompts like these exercise the full toolchain:
  • “Generate a cinematic portrait of a red fox in falling snow — give me 3 options”
  • “Animate the best one into a 5-second 720p video, gentle camera push-in”
  • “Write and sing a warm folk song about two foxes in the snow”
  • “Make a 5-second whoosh-and-impact sound effect for the scene transition”
  • “Add realistic sound effects to this clip” (with an uploaded video)
  • “Post the song to my BudgetPixel feed with the portrait as cover art”
  • “Enter the fox portrait in my clan’s current theme”
  • “Find a free stock photo of a misty forest for my blog header, and give me the credit line”

​
Where results go

MCP generations work like API generations, not like studio generations: each output is kept for 24 hours and is not added to your asset storage. Result links your agent shares are time-limited (about an hour; ask for the status again to get a fresh link). Every MCP job is listed in the developer console’s Requests tab, labeled MCP, where you can download it or save it to your assets. To keep something from chat, ask your agent to save it — the save_to_assets tool copies the output into your assets, where it appears in your workshops and counts against your storage like a studio generation.

​
MCP or the REST API?

MCP server

For AI agents and chat — Claude, ChatGPT, Cursor. OAuth sign-in, no keys, a human in the loop. Best when you are creating, with an agent doing the driving.

Developer API

For applications — API keys, per-model endpoints, full parameter control, webhooks-free polling. Best when your software is creating on a schedule or at volume.
Both surfaces expose the same models at the same credit prices, share the same 24-hour output window and the same spend limit, and both list their jobs in the developer console’s Requests tab (API key prefix or MCP).

​
FAQ

No. You sign in with your BudgetPixel account (Google SSO) during the connect flow — no keys to create or paste. API keys belong to the developer API, which is aimed at building applications.
Every paid plan — Starter, Basic, Premium, Pro and Ultra. Any account, Free included, can connect and use list_models and search_stock_images; generation, uploads, and posting require an eligible plan. Manage your plan at budgetpixel.com/subscription.
The same catalog as the API — Seedream, FLUX, GPT Image 2, Nano Banana, Qwen and more for images; SeeDance 2.0 / 2.0 Mini for video; Music 2.6, Lyria 3, and Mureka V9 for music (plus Sonilo Music for exact-length instrumentals); Sonilo SFX / Sonilo Video SFX for sound effects. The catalog updates automatically as models launch; list_models always returns the live list with prices.
MCP outputs are ephemeral, like API outputs: kept for 24 hours, listed under Requests in the developer console (labeled MCP), and never counted against your asset storage. Ask your agent to save a result (save_to_assets) — or use the save icon in the Requests tab — to copy it into your assets permanently, where it shows up in your workshops. Media links returned in chat are time-limited.
No — the posting tool is instructed to publish only when you explicitly ask, posts cost 10 credits each, and every post is labeled “via MCP” on the feed.