generate_image
Generate an image from a prompt (supports resolution, model_uri e.g. model/V_4_0/version/0).
LABSCO SUMMARY
Model training as a tool call is rare, and it is the reason to pick this over a generic generator.
Most image servers here generate from someone else's model. Being able to assemble a dataset and train your own from a conversation means the style becomes yours rather than borrowed — which matters when the output has to look like a brand. Note what the OAuth scopes are: identity only, so the authorisation screen is not where the capability boundary lives.
What it is
Ideogram's endpoint for their image product. The interesting third of it is not generation but training: you can build a dataset, upload assets to it and train a custom model from the same connection.
What you get
- generate_image and generate_images_bulk — from a prompt, with resolution and a model URI
- edit_image, remove_background, reframe_image, upscale_image — editing an existing image
- create_dataset, upload_dataset_assets, train_model — build a training set and train a custom model on it
- create_collection, upload_image, get_images_by_collection_id — organise the results
Requirements
An Ideogram account: the first time your client connects, a browser window opens for you to sign in, with no API key to handle. The scopes requested are identity only — openid, email and profile.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Generating on brand
Build a dataset from your own assets, train a model, then generate with it.
02
Producing variations at once
Bulk generation rather than one call per image.
03
Preparing an image for use
Remove the background, reframe to the aspect ratio you need, and upscale.
04
Keeping output organised
Create a collection and list what is in it later.
12 tools
Listed in project docs. Your client may show a different list.
generate_images_bulk
Generate multiple images (num_images).
edit_image
Edit an existing image.
remove_background
Remove image background (operation: remove_background).
reframe_image
Reframe/crop to aspect ratio or resolution.
upscale_image
Upscale an image (e.g. 2x).
upload_image
Upload assets back to a collection.
create_dataset
Create a training dataset.
upload_dataset_assets
Upload images to a dataset.
train_model
Train a custom image model.
create_collection
Create a named collection.
get_images_by_collection_id
List images in a collection.
BEFORE YOU INSTALL
What to know first
Tools you get
12 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- An Ideogram account (you sign in over OAuth when the client first connects)
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://mcp.ideogram.ai/mcpRequirements
- An Ideogram account: the first time your client connects, a browser window opens for you to sign in over OAuth — no API key. Usage draws on your Ideogram subscription.
