MCP Media Engine_
// PROMPT LIBRARY

Prompts you can run in your own agent.

Every entry on this page is a verbatim prompt you can paste into Claude, ChatGPT, Cursor, or Hermes — backed by MCP Media Engine. Each one shows the model, the credit cost, the surfaces it works in, and (where available) a verified MED job ID for the example image.

Looking for the API contract? See the docs. Need model + pricing detail? Visit /models.

run in your agent

Three lines and you're set.

Install MCP Media Engine once, then paste any prompt from this library into your agent. The job runs out-of-band and the asset URL comes back when the model is done.

install

Run via npx

Get a key at app.mcpmediaengine.com and set the env var.

npx -y mcp-media-engine

# set MEDIAENGINE_API_KEY in your env
# get a key at https://app.mcpmediaengine.com
paste a prompt

Use any entry below

Each card has a copy button. Drop the prompt into your agent verbatim.

// in your agent:
// "use the MCP media engine to generate an image with this prompt:
// transform the subject into a cinematic noir portrait, high-contrast studio rim lighting, deep shadows, monochrome with a subtle phosphor-green ambient glow on the cheek, 35mm film grain, sharp facial features, no text, no logos, no watermark"
pillars

Five pillars, one library.

The starter batch is balanced across five pillars — reach (selfie, pets, spaces) and revenue (product) on the FUNNEL side, plus the FOLLOW-style art pillar. Each pillar ships at least 2 entries so the routine has room to rotate.

Selfie transform

Selfie transforms — the highest-engagement pillar. img2img into a new medium.

3 entries

Pet transform

Pet portraits — soft watercolor or cartoon. Strong organic reach.

2 entries

Product shot

Product shots — for brands remaking ecommerce photography at scale.

2 entries

Space restyle

Space restyles — before/after room edits, save-bait format.

2 entries

Style art

Style art — pure style recipes with a constant subject.

4 entries

The starter batch (13)

Cinematic noir studio portrait generated from a selfie via MCP Media Engine img2img.
Selfie transform
Default Image · 1cr · 4:5

Selfie → noir portrait

Cinematic studio rim light, deep shadows, phosphor-green glow.

Open prompt
Painterly soft-light portrait generated from a selfie via MCP Media Engine img2img.
Selfie transform
Default Image · 1cr · 4:5

Selfie → painterly soft-light portrait

Loose oil-paint brushwork and warm golden-hour rim light.

Open prompt
Cyberpunk neon portrait generated from a selfie via MCP Media Engine img2img.
Selfie transform
Default Image · 1cr · 4:5

Selfie → cyberpunk neon

Magenta + teal neon rim lights, rain-soaked city bokeh.

Open prompt
Renaissance-style oil painting portrait generated from a pet photo via MCP Media Engine img2img.
Pet transform
Default Image · 1cr · 4:5

Pet → Renaissance oil painting

Chiaroscuro lighting, gilded museum frame, painterly brushwork.

Open prompt
Cosmic puppy portrait generated from a pet photo via MCP Media Engine img2img.
Pet transform
Default Image · 1cr · 4:5

Pet → cosmic puppy

Floats through a nebula of stars and pastel cosmic dust.

Open prompt
High-end product photograph generated from a sneaker photo via MCP Media Engine img2img.
Product shot
Default Image · 1cr · 1:1

Product → sneaker macro hero

Low-key studio lighting, glossy reflective surface, smoke wisps.

Open prompt
Luxury floating product photograph generated from a watch photo via MCP Media Engine img2img.
Product shot
Default Image · 1cr · 1:1

Product → watch floating

Suspended in mid-air with floating particles, cool slate backdrop.

Open prompt
Modern minimalist lounge restyle generated from a room photo via MCP Media Engine img2img.
Space restyle
Default Image · 1cr · 4:5

Room → magenta-lit lounge

Modern minimalist lounge with magenta accent lighting.

Open prompt
Studio Ghibli cottage reading nook restyle generated from a room photo via MCP Media Engine img2img.
Space restyle
Default Image · 1cr · 4:5

Room → Ghibli cottage reading nook

Hand-painted watercolor textures, candle glow, sleepy cat.

Open prompt
Watercolor painting of a lighthouse on a rocky coastline at dawn, soft wet-on-wet washes with paper texture.
Style art
Default Image · 1cr · 4:5

Watercolor coastline

Painterly wet-on-wet wash over a rocky shore.

Open prompt
Phosphor-green ASCII terminal frame enclosing a cosmic landscape — house-style Look A.
Style art
Default Image · 1cr · 4:5

House style — phosphor terminal ASCII frame

Phosphor-green ASCII terminal frame enclosing a cosmic landscape.

Open prompt
Cosmic landscape with a phosphor-green pixel corner glyph — house-style Look B.
Style art
Default Image · 1cr · 4:5

House style — phosphor minimal corner glyph

Cosmic landscape with a single phosphor-green corner signature.

Open prompt
Painterly composition with phosphor-green scanline overlay — house-style Look C.
Style art
Default Image · 1cr · 4:5

House style — phosphor scanline overlay

Painterly composition with thin phosphor-green scanlines.

Open prompt
3-step card

Same shape on every entry.

Each prompt page has the same 3-step setup card. The numbers don't change — only the prompt and the model vary.

  1. 01

    Install + key

    npx -y mcp-media-engine and an API key from app.mcpmediaengine.com.

  2. 02

    Attach your photo (if img2img)

    Attach your selfie, pet, or product photo to your agent chat — or paste any image URL.

  3. 03

    Paste the prompt

    Copy the verbatim prompt from the entry page and paste it. The agent submits the job and returns the asset URL when it's done.

works in

Same prompt, four agents.

Every prompt on this page is designed to run in any of these MCP-compatible agents. No per-agent fork needed.

  • ✓Claude Desktop (native MCP)
  • ✓ChatGPT (via MCP / REST)
  • ✓Cursor (MCP settings)
  • ✓Hermes (any MCP-compatible agent)
  • ✓Direct REST API (HTTP, no MCP required)

Policy: use your own photos — don't upload photos of other people without their consent. No celebrities, no third-party faces in our own posts. Every example image on this page is generated via MED itself; job IDs are listed on each entry page.

Ready to run a prompt in your own agent?

Get an API key See the model catalog