MCP App Store
by KeenEthics
Pixel Dojo icon

Pixel Dojo MCP Server for ChatGPT

By Pixel Dojo

Overview

Create images, videos and music without leaving ChatGPT. Pixel Dojo connects ChatGPT to a large catalog of image and video models. Describe what you want and get back the image or video, shown right in the chat. Turn a photo into a video, edit an image with words, upscale, add captions, make a product ad from a store link, or use the characters you saved in Pixel Dojo. Sign in with your Pixel Dojo account. Generations use the credits already in your account.

How to connect

  1. ChatGPT: Open the Pixel Dojo listing in the ChatGPT app directory and choose Connect. ChatGPT listing Pixel Dojo exposes 30 tools here.

Tools

pixeldojo_ad

ChatGPT
Marketing Studio: turn a product into a rendered video ad with voiceover. Requires product_url (name, description and images are extracted), or product_name plus product_image_urls (public http(s) URLs). Pick a style slug (default ugc-testimonial; full catalog at GET https://pixeldojo.ai/api/v1/marketing/presets), and optionally add presenter reference images, a location, a hook, and the exact spoken script. Returns the video URL, or a jobId to check with pixeldojo_status.

pixeldojo_audio

ChatGPT
Generate audio from one prompt: speech, multi-character dialogue, sound effects and background music (seed-audio, the default), or plain narration with preset voices (text-to-speech). Spends credits from the connected Pixel Dojo account. Returns an audio URL, or a jobId to check with pixeldojo_status.

pixeldojo_brand_kit

ChatGPT
The account's brand kit for Marketing Studio: logo, colors, fonts, voice, tagline and selling points. action import + url reads them from the brand's website (logo, palette and fonts from the page, the voice and claims from its words) and saves it; get shows it; update changes fields (colors as #RRGGBB, logo_url must be a PixelDojo upload). Free. Once set, every pixeldojo_ad, pixeldojo_campaign and pixeldojo_marketing call applies it automatically.

pixeldojo_build_character

ChatGPT
Build an original AI character or influencer from traits instead of photos, like Character Studio's builder: type (realistic, bold or extreme caricature, anime, 3D, cat, dog, fox, frog, insect, robot...), gender, age (adults only), body, height, wild proportions (egg body, long limbs, tiny waist), head shape (gigachad, mega jaw), hair, face features, style and accessories. action "traits" (free) lists every trait and option id; action "build" renders up to 4 takes from picks (and/or randomize). Keep one with pixeldojo_save_character.

pixeldojo_campaign

ChatGPT
Generate a coherent product launch package (hero image + N lifestyle variants + optional vertical video) from one URL or product profile. Composes hero / lifestyle / video models server-side; returns assets in one call or a handoff with campaignId to poll via pixeldojo_campaign_status.

pixeldojo_campaign_status

ChatGPT
Poll a campaign by campaignId returned from pixeldojo_campaign. Returns assets when every sub-job is done, or a handoff describing what is still in flight.

pixeldojo_caption

ChatGPT
Burn animated word-by-word captions onto a video with speech, the short-form look for TikTok, Reels and Shorts: the spoken word lights up, placed above the platform buttons. Pass video_url; optional style (pop, highlighter, clean) and highlight_color (#RRGGBB for a brand color). 5 credits.

pixeldojo_character

ChatGPT
Generate or edit consistent characters across shots. Pass reference_image_urls (up to 9) to lock identity — send every photo of the person you have, since more angles hold the face far better than one. Defaults to seedream-5.

pixeldojo_clipper

ChatGPT
Turn a long talking video (podcast, stream, interview, webinar, 2 minutes to 2 hours) into its best moments as vertical 9:16 clips (15-60 s each) with word-by-word captions, framed on whoever is talking (two people on screen are stacked). Upload the video first with pixeldojo_upload. Costs 3 credits per minute of the source (at least 15), charged only when the clips are delivered; tell the user the price before starting. Then call status until done (about 5-15 minutes).

pixeldojo_edit

ChatGPT
Edit an existing image with a text instruction. Defaults to wan-2.7-image-edit; pass model to pick another edit-capable apiId. Supports up to 9 reference images for multi-image composition. Pass reference images as public http(s) URLs via image_url or image_urls.

pixeldojo_episode

ChatGPT
Make a finished narrated faceless video (explainer, history, kids story) from one topic: script, scene visuals, AI narration, music bed, stitched export saved to the Library. Phased: create is free and returns a credit quote; produce is charged and advances one step per call (poll every ~30s until it returns the video URL); status is free.

pixeldojo_from_url

ChatGPT
Extract a product profile from a product page URL: name, description, image URLs (the first three are listed), and the extraction method used. Works on Shopify, BigCommerce, WooCommerce, or any page with JSON-LD / OpenGraph product metadata. Free. pixeldojo_campaign and pixeldojo_ad accept a product URL and run this extraction themselves; call this directly to check the product data first, or to reuse its images in other tools.

pixeldojo_library

ChatGPT
Search your Library, newest first. source=media (default): saved media (permanent) and recent API/MCP generations (deleted 1 hour after they finish), as URLs to reuse as references. source=characters: saved Character Studio characters and elements, each usable as @Name in any prompt.

pixeldojo_make_image_gpt_image_2

ChatGPT
Makes one still image from a prompt with GPT Image 2: exact text, layouts and graphics. Optional: aspect_ratio, image_url or image_urls for reference photos. Spends credits from the connected Pixel Dojo account. Returns the finished image, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_image_nano_banana_2_1

ChatGPT
Makes one still image from a prompt with Nano Banana 2.1: quick images that follow reference photos. Optional: aspect_ratio, image_url or image_urls for reference photos. Spends credits from the connected Pixel Dojo account. Returns the finished image, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_image_nano_banana_pro

ChatGPT
Makes one still image from a prompt with Nano Banana Pro: detailed scenes and readable text. Optional: aspect_ratio, image_url or image_urls for reference photos. Spends credits from the connected Pixel Dojo account. Returns the finished image, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_image_seedream_5

ChatGPT
Makes one still image from a prompt with Seedream 5: the default image model. Optional: aspect_ratio, image_url or image_urls for reference photos. Spends credits from the connected Pixel Dojo account. Returns the finished image, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_image_seedream_5_5

ChatGPT
Makes one still image from a prompt with Seedream 5.5: the default image model. Optional: aspect_ratio, image_url or image_urls for reference photos. Spends credits from the connected Pixel Dojo account. Returns the finished image, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_video_kling_4_0

ChatGPT
Makes one short video from a prompt with Kling 4.0: a scene up to 30 seconds written as a shot list, with dialogue in quotes. Optional: aspect_ratio, duration, resolution, image_url or image_urls for reference photos (image_url is the starting frame). Spends credits from the connected Pixel Dojo account. Returns the finished video, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_video_minimax_h3_turbo

ChatGPT
Makes one short video from a prompt with MiniMax H3 Turbo: the lowest-cost video, from a prompt, a photo or up to 9 reference images. Optional: aspect_ratio, duration, resolution, image_url or image_urls for reference photos (image_url is the starting frame). Spends credits from the connected Pixel Dojo account. Returns the finished video, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_video_seedance_2_5

ChatGPT
Makes one short video from a prompt with Seedance 2.5: the default video model, from a prompt or a starting image. Optional: aspect_ratio, duration, resolution, image_url or image_urls for reference photos (image_url is the starting frame). Spends credits from the connected Pixel Dojo account. Returns the finished video, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_make_video_seedance_2_5_flash

ChatGPT
Makes one short video from a prompt with Seedance 2.5 Flash: the default video model, from a prompt or a starting image. Optional: aspect_ratio, duration, resolution, image_url or image_urls for reference photos (image_url is the starting frame). Spends credits from the connected Pixel Dojo account. Returns the finished video, or a jobId to check with pixeldojo_status when it takes longer than 30 seconds.

pixeldojo_marketing

ChatGPT
Marketing Studio templates beyond video ads. templates lists them free with real example outputs. image applies an image template to a product: static ads, product shots, posters, marketplace listings (pure white for Amazon/Shopify), UGC photos, headline spelled exactly, 1-8 at a time at the engine price; with reference_ad_url it rebuilds an existing ad with this product (ad multiplier). motion renders code-built motion graphics with exact words, brand colors and logo: kinetic-headline, feature-callouts, count-up, price-drop, logo-sting (2 credits each). end_card adds the brand logo, tagline and button after a finished video ad (1 credit per 30 s). The brand kit (pixeldojo_brand_kit) fills colors, logo, headline and selling points unless brand_kit: false.

pixeldojo_overlay

ChatGPT
Add short-form ad text layouts to a finished video, exact text in the brand color, clear of the TikTok/Reels/Shorts UI: hook (title over the first seconds), callout (lower-third label), review (stars, quote, name), progress_bar, countdown (ticking timer), price_tag (new price, old one struck through), offer ("50% OFF" badge) and end_card (logo, headline, button, web address over the held last frame). Pass video_url plus any of them; one call does all. 2 credits.

pixeldojo_perform

ChatGPT
Make a saved Character Studio character perform: a dance, a trend or a star moment (AI Dance, Sassy Dance, Shoulder Shimmy, Hair Flip, Catwalk, Peace Wink, Red Carpet, Award Win...) as a share-ready 5 s video. action "list" (free) gives the presets and prices; action "run" takes character (name or @Name) and preset. Usually handed off; poll with pixeldojo_status.

pixeldojo_save

ChatGPT
Save a generated image or video into the user's My Media library permanently ("save this", "keep it"). Results otherwise expire 1 hour after they finish. Pass the result URL; it is safety-checked before it is kept.

pixeldojo_save_character

ChatGPT
Save a character (a person, from 3-5 photos) or an element (product, outfit, location, prop, style) to the user's Character Studio library. Afterwards write @Name in any prompt to use it. List saved ones with pixeldojo_library source=characters.

pixeldojo_status

ChatGPT
Check once, without waiting, on a jobId that a generation tool returned instead of an asset after its 30s wait. Free. Returns asset URLs when complete, the failure reason if it failed, or the current state and job age if still running. Campaign ids go to pixeldojo_campaign_status; films report progress through pixeldojo_film with action "status".

pixeldojo_upscale

ChatGPT
Enhance an image or video. Magnific (default) supports configurable scale_factor and creativity; face-enhance for portraits; video-upscaler (FlashVSR, up to 4K) for clips — pass video_url plus video_duration in seconds.

pixeldojo_video

ChatGPT
Video Studio verbs for an existing clip, on the same engines the studio uses. verb=change restyles or edits a clip (prompt + video_url, optional reference images). verb=move puts a character image into a driving video's motion (video_url + image_url + video_duration). verb=extend continues a clip forward, or backward on the default engine (prompt + video_url, optional duration and direction). Omit model for the studio default; engine-specific settings go in params with an explicit model. To make a new video, use pixeldojo_generate. Returns asset URLs, or a jobId for pixeldojo_status when the job outlasts the 30s wait. Media must be public http(s) URLs.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/pixel-dojo"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/pixel-dojo)