Skip to main content

PixelDojo MCP & Skills
for AI image, video and audio

Connect the PixelDojo MCP server to Claude, Cursor, Codex and more, then generate images, video, and audio straight from your prompts. 140+ models, one connection.

Hosted server with browser sign-in. Nothing to install, no API key.

  1. 1

    Paste one command in your terminal

    The hosted server carries every skill and stays current.

    claude mcp add --transport http pixeldojo https://pixeldojo.ai/mcp
  2. 2

    Approve in your browser

    On first use a PixelDojo window opens. Sign in, click Approve, done. No API key to copy.

  3. 3

    Ask for anything

    “Generate a cinematic portrait, Tokyo rain.” Images, video, audio, films, ads and your library are all live.

Then add the skills bundle

11 ready-made workflows for ads, UGC, faceless video and film. See them

npx skills add https://pixeldojo.ai/pixeldojo-skills.zip

Prefer plain HTTP? Every model has a REST endpoint: API documentation.

Watch it work

One message in your AI chat becomes an image, a video, an ad, a short film or a talking presenter.

What your agent makes

Every tile is a real PixelDojo output, made from the prompt under it. Copy the prompt, or open it straight in Claude.

UGC

UGC Testimonial

A creator holds your product to camera and says the exact line you write.

pixeldojo_ad

Use PixelDojo to make a UGC testimonial ad for my vitamin C serum. Bright bathroom, the creator holds the bottle up to camera and says: "Two weeks on this serum and my skin has never looked this bright."

Try in Claude
Ad LocalizerPaid ads

Ad Localizer

Translate a static ad for a new market. Layout, product and brand stay put.

pixeldojo_edit

Use PixelDojo to localize this static ad into Spanish. Translate the headline and the button, keep the typeface, layout, product and logo exactly as they are.

Try in Claude
UGC

Virtual Try-On

Put a flat-lay garment on a model in a real fitting room.

pixeldojo_ad

Use PixelDojo to make a virtual try-on ad for this sweater. Fitting room mirror, natural light, the model turns to show the fit.

Try in Claude
Faceless

Faceless Explainer

Script, scenes, narration and music from one topic, exported as one video.

pixeldojo_episode

Use PixelDojo to make a 60-second faceless explainer about why we yawn, in a paper diorama style. Vertical, with narration and a music bed.

Try in Claude

What it can do

Ask in plain words. Your agent picks the right tool, runs it on your PixelDojo credits and hands back the result.

  • An image made with pixeldojo_generate

    Images and video from one prompt

    Your agent describes it; PixelDojo picks the right model and hands back a URL.

    pixeldojo_generate
  • An image edited with pixeldojo_edit

    Edit any image in plain English

    Change the background, objects, lighting or style just by describing it.

    pixeldojo_edit
  • A consistent character made with pixeldojo_character

    The same character in every scene

    One reference image keeps a face consistent from shot to shot.

    pixeldojo_character
  • An image upscaled with pixeldojo_upscale

    Upscale up to 16× sharper

    Print-ready detail from any image, for ads, prints and big screens.

    pixeldojo_upscale

  • Narration or a whole sound scene

    A single voice, or up to two minutes of scored sound, from one prompt.

    pixeldojo_audio
  • A frame from a video ad made with pixeldojo_ad

    A video ad from any product

    A product URL or photos plus an ad style becomes a finished ad in one call.

    pixeldojo_ad
  • A frame from a short film made with pixeldojo_film

    A short film from an idea

    Script, storyboard, clips with dialogue and a score, stitched into one film.

    pixeldojo_film
  • A lifestyle image from a pixeldojo_campaign run

    A campaign from one product page

    A hero image, lifestyle variants and an optional vertical video, made in parallel.

    pixeldojo_campaign

Plus 11 ready-made workflows

Ad Localizer, Ad Resizer, Headline Variants and more: skills that teach your agent the whole job, in Claude Code, Codex, Cursor and 75+ other agents. Connect the MCP server first, then run:

npx skills add https://pixeldojo.ai/pixeldojo-skills.zip
Or download the .zip
See every tool, with inputs, outputs and cost (19 tools, 11 workflows)

Create

Make or transform one piece of media.

pixeldojo_generate

Create a new image or video; optional presets and supported first-frame references.

Input
Prompt; optional model, preset, aspect ratio, duration, or image URL.
Output
Asset URL, or a job ID and status URL for longer renders.
Cost
Selected model rate; charged only when generation succeeds.
Schema & examples
pixeldojo_edit

Change an existing image while preserving the parts you do not mention.

Input
Edit instruction plus 1–9 image URLs (local image paths work with the local npx install).
Output
Edited image URL or an async job handoff.
Cost
Selected edit-model rate; charged only on success.
Schema & examples
pixeldojo_character

Render the same person in a new scene from their reference photos.

Input
Prompt plus reference_image_urls (up to 9 photos of the person, most important first) on every identity-locked call.
Output
Character-consistent image URL or an async job handoff.
Cost
Selected character-model rate; charged only on success.
Schema & examples
pixeldojo_upscale

Increase image resolution with conservative or creative enhancement, or upscale a video clip.

Input
Image URL (or a video URL plus its length in seconds); optional upscaler and scale factor.
Output
Upscaled image or video URL, or an async job handoff.
Cost
Selected upscaler rate; charged only on success.
Schema & examples
pixeldojo_audio

Create narration or a complete audio scene with dialogue, effects, and music.

Input
Script or scene prompt; optional voice, up to 3 hosted reference clip URLs, format, and speed.
Output
Audio URL or a job ID and status URL.
Cost
Seed Audio or text-to-speech model rate; charged only on success.
Schema & examples

Produce

Compose several generation steps into a production.

pixeldojo_storyboard

Generate one video storyboard preview from one scene brief.

Input
Brief; optional video model, aspect ratio, and duration.
Output
One video preview URL or an async job handoff.
Cost
One video generation at the selected model rate. Use film for multi-shot work.
Schema & examples
pixeldojo_ad

Turn a product URL or photos into one rendered video ad with voiceover.

Input
Product, style, and optional presenter, location, hook, script, quality, and duration.
Output
Rendered ad URL or a job ID and status URL.
Cost
Varies by engine, quality, resolution, and 4–15 second duration.
Schema & examples
pixeldojo_film

Plan and produce a multi-shot short film with dialogue, score, and stitched export.

Input
Idea or script, look, aspect ratio, and target length.
Output
Free plan and estimate first; then film workspace and final video URL.
Cost
Planning is free; production is roughly 35–40 credits per 5-second shot plus soundtrack.
Schema & examples
pixeldojo_campaign

Produce a hero image, lifestyle variants, and an optional vertical launch video.

Input
Product URL/profile, tone, 1–8 variants, and video options.
Output
Campaign ID plus an ordered asset set.
Cost
Hero, lifestyle shots, and video are each billed at their model rate; the total shows in campaign status.
Schema & examples
pixeldojo_video

Change, move, or extend a video you already have: restyle a clip, put a character into it, or lengthen it.

Input
Verb (change, move, or extend), source video URL, prompt; optional reference images, clip length in seconds, and engine.
Output
Edited video URL or an async job handoff.
Cost
Selected engine rate, metered by clip length on most engines; charged only on success.
Schema & examples
pixeldojo_episode

Make a finished narrated faceless video (explainer, history, kids story) from one topic.

Input
Topic; optional category, visual style, aspect ratio, 60–300 second length, voice, and music.
Output
Free script and credit quote first; then the finished video URL, saved to your Library.
Cost
Planning is free; production is charged step by step at the same prices as Faceless Studio.
Schema & examples

Bring inputs

Turn local files and product pages into reusable inputs.

pixeldojo_upload

Upload a local image or video so another skill can use it by URL.

Input
Absolute local file path (local npx install only; the hosted server takes URLs).
Output
Temporary public URL that expires after about 24 hours.
Cost
Free; no generation credits.
Schema & examples
pixeldojo_from_url

Extract a structured product profile from a public product page.

Input
Product-page URL.
Output
Name, description, image URLs, and source metadata.
Cost
Free; no generation credits.
Schema & examples

Manage

Track jobs, find assets, retain outputs, and reuse repeatable chains.

pixeldojo_status

Check a single long-running generation job.

Input
Job ID returned by another skill.
Output
Current state, failure/refund detail, or completed asset URLs.
Cost
Free; polling never consumes generation credits.
Schema & examples
pixeldojo_campaign_status

Check all sub-jobs in a campaign.

Input
Campaign ID returned by pixeldojo_campaign.
Output
Progress, warnings, total charged credits, and completed assets.
Cost
Free; polling never consumes generation credits.
Schema & examples
pixeldojo_library

Find permanent Library items and recent API/MCP generations.

Input
Optional prompt query, model, modality, and result limit.
Output
Reusable asset URLs with source and creation metadata.
Cost
Free and read-only.
Schema & examples
pixeldojo_save_workflow

Save a named multi-step skill chain for reuse.

Input
Workflow name and ordered skill steps; {{prev}} can feed the prior result forward.
Output
Saved workflow definition.
Cost
Saving is free; generations run later use normal model rates.
Schema & examples
pixeldojo_run_workflow

Run a previously saved workflow with new inputs.

Input
Workflow name plus values for its input placeholders.
Output
Final result, or a handoff when a step needs more time.
Cost
Sum of the generation steps; polling and orchestration are free.
Schema & examples
pixeldojo_list_workflows

List saved workflows before choosing one to run.

Input
No required input.
Output
Workflow names and saved step definitions.
Cost
Free and read-only.
Schema & examples

Workflows

The skills bundle, installed with the command above.

  • Ad Localizer

    Paid ads

    /pixeldojo-ad-localizer

    Translate and adapt static image ads into other languages and markets with PixelDojo, keeping the layout, product and brand intact.

  • Ad Resizer

    Paid ads

    /pixeldojo-ad-resizer

    Adapt one static ad to other placements and aspect ratios (1:1 and 4:5 feed, 9:16 Stories and Reels, 16:9) with PixelDojo while keeping the copy and product clear.

  • Headline Variants

    Paid ads

    /pixeldojo-headline-variants

    Produce several versions of a static ad with different headlines or calls to action for testing, using PixelDojo image edits.

  • Hook Variants

    Paid ads

    /pixeldojo-hook-variants

    Make several versions of a product video ad that differ only in the opening 1 to 2 seconds, for hook testing, with PixelDojo.

  • Static to Motion

    Paid ads

    /pixeldojo-static-to-motion

    Animate a finished static ad or product image into a short motion ad with PixelDojo while keeping text and logos legible.

  • Research to Ads

    Paid ads

    /pixeldojo-research-to-ads

    Turn a product page into a first batch of static ad concepts across different angles, rendered with PixelDojo.

  • UGC Ad

    UGC

    /pixeldojo-ugc-ad

    Make a UGC-style video ad (testimonial, unboxing, try-on, fit check, day in the life) for a product with PixelDojo.

  • Faceless Video

    Faceless

    /pixeldojo-faceless-video

    Make a narrated faceless video (explainer, history, kids story) from one topic with PixelDojo: script, scene visuals, narration, music and one exported file.

  • Short Film

    Film & story

    /pixeldojo-short-film

    Make a short film or music video from an idea with PixelDojo: screenplay, storyboard, clips with dialogue, soundtrack and a stitched export.

  • Consistent Character

    Film & story

    /pixeldojo-consistent-character

    Keep the same person or character across many images (scenes, outfits, angles) with PixelDojo.

  • Product Launch Pack

    Product

    /pixeldojo-product-launch

    Create a product launch package (hero image, lifestyle shots and a vertical video) from one product URL with PixelDojo.

Human Handoff

Your agent generates.
You finish in Canvas.

MCP and API outputs stay available for 1 hour, so download anything you want to keep. Then keep working by hand in Canvas: edit, upscale, animate, and chain models in one session.

Open Canvas
PixelDojo Canvas: chain models in one freeform session

REST API

Prefer plain REST?

Everything the MCP server does is a plain HTTP call, so any agent or script that can fetch a URL can use it.

  • One endpoint pattern for all 140+ image, video and audio models.
  • An OpenAPI 3.1 spec, a JSON schema per model, and an LLM-ready reference.
  • Async jobs with status polling or webhooks; failed jobs are refunded automatically.
import { PixelDojoClient } from "@pixeldojo/sdk";

const pd = new PixelDojoClient({ apiKey: "pd_your_api_key" });

// Generate an image and wait for the result
const job = await pd.generate("google-nano-banana", {
  prompt: "A fantasy castle on a cliff at sunset",
  aspect_ratio: "16:9",
});

console.log(job.assets[0].url);

Got any questions left?

Questions & Answers

Frequently Asked Questions

The most frequently asked questions, answered

Your agent. Every model.

One install. 140+ models. Connect in minutes and create your first image right away.

View install optionsGet API key

npx @pixeldojo/mcp init