Skip to content
Agentmart
Submit a tool

PixelDojo

Generate images, video, audio and short films with 140+ AI models from any MCP client.

Connector by pixeldojo.aiOfficial · Domain verified by the MCP Registry

IndexedMITLocal (stdio)Remote (HTTP)
Write a review

Install

Works with Claude Code, VS Code, Codex, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/pixeldojo-ai-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://pixeldojo.ai/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate images, video, audio and short films with 140+ AI models from any MCP client.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 6 write · 0 delete · 8 not yet classified
Secrets
1 (API keys, tokens or passwords)
Install scripts
None found
Runs as
Node.js package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • pixeldojo_campaign_status
  • pixeldojo_from_url
  • pixeldojo_library
  • pixeldojo_list_workflows
  • pixeldojo_status

Write 6 · Create, change, send or run things.

  • pixeldojo_edit
  • pixeldojo_episode
  • pixeldojo_film
  • pixeldojo_run_workflow
  • pixeldojo_save_workflow
  • pixeldojo_upload

Not yet classified 8 · We could not tell from the name and description.

  • pixeldojo_ad
  • pixeldojo_audio
  • pixeldojo_campaign
  • pixeldojo_character
  • pixeldojo_generate
  • pixeldojo_storyboard
  • pixeldojo_upscale
  • pixeldojo_video

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • PIXELDOJO_API_KEY

Network hosts it talks to 1

  • pixeldojo.ai · found in remote endpoint, install command

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • pixeldojo_ad

    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 / product_image_paths. 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

    Generate audio: speech, multi-character dialogue, sound effects, and background music from one prompt (Seed Audio 1.0 by default; plain text-to-speech available). Voice cloning takes hosted reference clip URLs in audio_urls; local audio files are not accepted. Returns an audio URL, or a jobId for pixeldojo_status.

  • pixeldojo_campaign

    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

    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_character

    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_edit

    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. For reference images: pass image_url(s) for hosted URLs or image_path(s) for absolute local file paths (skill uploads to 24h temp storage automatically).

  • pixeldojo_episode

    Make a finished narrated faceless video (explainer, history, kids story) from one topic: script, scene visuals, AI narration, music bed, stitched export saved to My Media. 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_film

    Make a finished short film from one idea: screenplay, storyboard frames (AI-reviewed), video clips with spoken dialogue, scene-synced soundtrack, stitched export. Or a music video: pass song_path (a local file) or song_url (your own PixelDojo upload from pixeldojo_upload, never a third-party link) with optional lyrics; the film is cut to that song, each clip lip-synced to its slice on the studio music video engine, and no score is composed: the export plays the song. Phased: plan is free; produce starts charged generation; status advances production (poll every ~30s).

  • pixeldojo_from_url

    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_generate

    Generate an image or video from a prompt with any model in the PixelDojo catalog. With no `model`, a prompt runs on seedream-5, which makes still images only. For a video, name seedance-2-5, which works from a prompt alone or a starting image. To try video takes cheaply, set draft: true (a 480p Seedance 2.5 draft), then upgrade_draft the one the user picks to 1080p. If a provider refuses the content, retry once on wan-3-0-video (video) or seedream-5 (images), the least-restricted models. For a multi-shot film or a music video synced to a song use pixeldojo_film; to change, move or extend an ex…

  • pixeldojo_library

    Search your media library: saved My Media items (permanent) and recent API/MCP generations (deleted 1 hour after they finish), newest first. Returns asset URLs to reuse as reference inputs.

  • pixeldojo_list_workflows

    List your saved workflows with step counts and run totals.

  • pixeldojo_run_workflow

    Run a saved workflow by name. Pass inputs for its {{input.<key>}} placeholders; each step feeds the next via {{prev}}.

  • pixeldojo_save_workflow

    Save a named multi-step skill chain (generate → edit → upscale …). String args may contain {{input.<key>}} and {{prev}} placeholders. Saving to an existing name overwrites it.

  • pixeldojo_status

    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".

Show 4 more tools
  • pixeldojo_storyboard

    Generate one short video clip (a single shot, not a multi-panel storyboard) from a scene brief. A text-only brief runs on veo-3.1-fast unless `model` names another allowed video model. With image_url (reference still) or video_url (source clip) and no `model`, it runs on seedance-2-reference, with the same reference routing as pixeldojo_generate. For a multi-shot film with dialogue and a soundtrack, use pixeldojo_film.

  • pixeldojo_upload

    Upload a local image, video or audio file (JPEG, PNG, WebP, GIF up to 50MB; MP4, WebM, MOV up to 200MB; MP3, WAV, M4A, AAC, OGG, FLAC up to 50MB) and get back a public URL that expires after 24 hours. Free. Pass an audio URL as song_url to pixeldojo_film for a music video. Pass the URL as image_url (stills) or video_url (clips) to tools that take hosted URLs only, such as pixeldojo_character, pixeldojo_storyboard and pixeldojo_upscale. pixeldojo_generate, pixeldojo_edit and pixeldojo_ad take local paths directly and need no separate upload.

  • pixeldojo_upscale

    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

    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…

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Sep 30, 2026 (28 days ago)
Last release
Oct 7, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
ai.pixeldojo/mcp
Version
0.20.0
Auth
Auth not stated, API key
Packages
npm @pixeldojo/mcp
License
MIT
Repository
github.com/blovett80/pixeldojo-mcp
Website
pixeldojo.ai/skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

PixelDojo MCP server. Agent Mart. https://agentmart.dev/connectors/pixeldojo-ai-mcp (last updated 2026-10-24)