Image & Video tools
your AI agents can
actually call.

MCP install for Claude Code, Cursor, OpenClaw — or REST.137+ image and video models, one auth, async by default.

quick start

# 1. Install in your Claude Code / Cursor / OpenClaw project
npx @pixeldojo/mcp init

# 2. Set your API key
export PIXELDOJO_API_KEY=pd_your_api_key

# 3. Restart your agent — it now has these tools:
#    pixeldojo:generate    Any prompt -> image or video
#    pixeldojo:character   Consistent characters across shots
#    pixeldojo:storyboard  Multi-shot scenes from one brief
#    pixeldojo:upscale     Enhance any image
#    pixeldojo:status      Poll long-running jobs

# Get your key: https://pixeldojo.ai/api-platform/api-keys

Install

Three paths to the same five tools. Pick whichever your editor or agent uses.

Cowork

Drag-and-drop plugin. No JSON to edit before drop.

Download pixeldojo.plugin

1. Open the .plugin archive, edit .mcp.json, paste your PIXELDOJO_API_KEY.
2. Drag the file into Cowork.
3. All five tools appear. Done.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pixeldojo": {
      "command": "npx",
      "args": ["-y", "@pixeldojo/mcp"],
      "env": { "PIXELDOJO_API_KEY": "pd_..." }
    }
  }
}

Cursor / OpenClaw / Codex

Same config shape. Drop into ~/.cursor/mcp.jsonor your client's equivalent.

{
  "mcpServers": {
    "pixeldojo": {
      "command": "npx",
      "args": ["-y", "@pixeldojo/mcp"],
      "env": { "PIXELDOJO_API_KEY": "pd_..." }
    }
  }
}

Any client that speaks stdio-transport JSON-RPC works. Spawn npx -y @pixeldojo/mcp, pass your key in PIXELDOJO_API_KEY.

Named Skills

Named skills

One install, four skills. Your LLM picks the right one per task.

pixeldojo:generate

Any prompt.
Best model, automatically.

Your agent describes what it needs in plain English. PixelDojo routes to the right model — photorealism, text rendering, video — and hands back a URL.

✓130+ models, one skill to call
✓Images, video, editing — same call shape
✓Credits deducted only on success

Terminal

>_ Generate a cinematic portrait, Tokyo rain, neon reflections

PixelDojo

Routing to flux-1.1-pro...

Job queued: job_k9mXpQ2r

✓ output: https://pixeldojo.ai/r/…/portrait.png

✓ 1024×1024 PNG · 1 credit

>_ _

Terminal

>_ Alex presenting a new phone, marble desk, soft studio light

PixelDojo

Loading ref: alex_character.png...

Routing to flux-kontext...

Job queued: job_3vNaL8wK

✓ output: https://pixeldojo.ai/r/…/alex-desk.png

✓ Consistency preserved · 2 credits

>_ _

pixeldojo:character

Same character.
Any scene.

Pass a reference image once. Your agent reuses the character across any number of scenes — different backgrounds, poses, lighting — while preserving their face and features.

✓Prompt evolves the scene; the character stays locked
✓Works with Flux Kontext, Ideogram Character, and more
✓No LoRA training required — just a reference image URL

pixeldojo:storyboard

One brief.
N shots, planned and generated.

Your agent writes the brief. PixelDojo breaks it into shots, decides which are images and which are video, generates them in parallel, and returns an ordered array of output URLs.

✓Mix image and video shots in the same storyboard
✓Shot planning included — no need to prompt each frame individually
✓Returns an ordered array your agent can pass to an editor or exporter

Terminal

>_ 60s product reveal: teaser, unboxing, close-up, lifestyle

PixelDojo

Planning 4 shots...

Shot 1/4 ✓ teaser (image)

Shot 2/4 ✓ unboxing (video)

Shot 3/4 ✓ close-up (image)

Shot 4/4 ✓ lifestyle (video)

✓ outputs: [4 URLs] · 6 credits

>_ _

Terminal

>_ Upscale this product photo to 4K, enhance detail

PixelDojo

Analyzing: 1024×1024 → 4096×4096

Routing to magnific-upscaler...

Job queued: job_8tHjR5mN

✓ output: https://pixeldojo.ai/r/…/upscaled.png

✓ 4096×4096 PNG · 2 credits

>_ _

pixeldojo:upscale

Any image.
Up to 16× sharper.

Pass any image URL. Your agent gets back a high-res version — no upload step, no format conversion. Conservative mode preserves the original; creative mode can enhance textures and fine detail.

✓2× to 16× magnification depending on model
✓Works on any image URL — no upload required
✓Conservative and creative upscale tiers

Preset Library

Try a preset, no prompt-writing required

Curated starting points across 60 workflows. Refresh for a different mix.

Canvas

Chain models in Canvas.

Generate, edit, upscale, animate — all in one freeform session. Hand the chain off to your LLM, or drive it yourself in the browser.

PixelDojo Canvas — chain models in one freeform session

API Design

Built for automation

Every detail is designed for machines that call APIs, not humans clicking buttons.

130+ AI Models

Image generation, video generation, upscaling, and editing. One auth.

Async by Default

Submit a job, get a job ID. Poll the status URL or register a webhook.

Per-Model Schemas

Every model has a JSON schema endpoint. Your agent knows the request shape before calling.

No Browser Needed

Pure REST API. No UI scraping, no headless browser, no screenshots.

Credit-Based Pricing

Pay per generation with credits. No subscription required to use the API.

LLM Discovery

llm.txt, OpenAPI 3.1 spec, and AI plugin manifest for zero-config agent integration.

Endpoint reference

Method	Endpoint	Description
`GET`	`/api/v1/models`	List all available models
`GET`	`/api/v1/models/{apiId}/schema`	Get the JSON schema for a model
`POST`	`/api/v1/models/{apiId}/run`	Submit a generation job
`GET`	`/api/v1/jobs/{jobId}`	Check job status and get output URLs
`POST`	`/api/v1/jobs/{jobId}/webhook`	Register a webhook for completion