Give your agent
a camera crew

Connect APImage to Claude, Cursor, ChatGPT or Codex and let it generate images, video and lip sync directly. One endpoint, one API key, 19 tools.

Get your API key
Read the docs

https://mcp.apimage.org/mcp

Where you work

Connect Claude Code

Anthropic's terminal coding agent

Claude Code docs
  1. 1

    Add the server

    Run this in your terminal. Drop -s user to scope it to the current project only, and replace the placeholder with your APImage API key:

    Terminal
    claude mcp add --transport http apimage https://mcp.apimage.org/mcp \
  --header "Authorization: Bearer sk_your_api_key" -s user
  2. 2

    Verify the connection

    Start Claude Code, run /mcp, and confirm apimage is connected. You'll see tools like generate_image, generate_video and check_credits.

    In Claude Code
    /mcp

Any client that speaks remote HTTP MCP works. Prefer plain REST?

How MCP works

Ask in plain language. Your assistant calls APImage, and the finished file lands in your media library.

ClaudeAPImage connected

Take this product shot and give me a 15-second vertical ad with a creator holding it.

I'll write the concept and script first, then generate the creator performance with the product details held consistent and native captions burned in.

generate_videoDone
Generation input

Generate a 15-second 9:16 UGC video using the attached creator and product. Casual piece-to-camera delivery, close on the pack shot.

Seedance 2.09:1615sAudio

Done. Concept, script, creator performance and a social-ready vertical cut, saved to your media library.

Result
9:16
424k+134%104k+95%

Generated over MCP, saved to your library

Everything, exposed

The full surface of APImage, callable by name. Reads are free, generations spend the same credits as the dashboard.

Create

  • generate_image

    Text to image on Flux 2 or GPT Image 2, up to 4K

  • generate_video

    Seedance 2.0 text, image or video to video

  • generate_lip_sync

    Talking avatar from an image and your audio

  • edit_image

    Enhance, relight, color grade, upscale or inpaint

Refine

  • remove_background

    Transparent PNG or WebP cutout

  • replace_background

    Swap the scene, keep the subject

  • analyze_image

    Describe, OCR or answer questions about an image

  • enhance_prompt

    Rewrite a prompt for image or video, free

Manage

  • list_brand_assets

    Browse characters, products, backgrounds, palettes

  • create_brand_asset

    Save a new reusable asset

  • generate_brand_asset

    Generate an image and save it in one step

  • check_credits

    Balance, monthly usage and tier, free

Plus job status, history and full brand-asset CRUD.

Inside your assistant

Every model available in the dashboard is available to your agent.

Seedance 2.0Flagship

BytePlus

Seedance 2.0

Cinematic video up to 1080p. The one you ship ads with.

from 38 credits per 5s

Seedance 2.0 FastFast

BytePlus

Seedance 2.0 Fast

Same engine, up to 720p, cheaper. Built for testing hooks in bulk.

from 30 credits per 5s

Flux 2 MaxPlus and up

Black Forest Labs

Flux 2 Max

Maximum detail and prompt adherence. Your hero shots live here.

3 to 9 credits

GPT Image 2

OpenAI

GPT Image 2

The best text rendering there is. Thumbnails, posters, packaging.

3 to 9 credits

Flux 2 Pro

Black Forest Labs

Flux 2 Pro

High quality at a working price. The everyday workhorse.

1 to 3 credits

Flux 2 Klein 9B

Black Forest Labs

Flux 2 Klein 9B

Fast and reliable. Ideal for iterating before you commit.

1 to 2 credits

Developer questions

Your agent could be shipping video.
Two minutes from now

Generate a key, paste one line of config, and ask for a video.

Get your API key