General research
Graphical abstract maker
Turn an abstract into a one-panel visual summary in the style journals ask for.
20 credits / figure|create_figure, get_figure
Once connected, say this to your agent
Read my abstract and make a Cell-style graphical abstract with three panels.
SourcesBest-in-class figure model, tested by us
Works withClaude · ChatGPT · Codex · Cursor · Gemini CLI · REST API
Toolscreate_figure, get_figure
Example
YOU SAY TO YOUR AGENT
Read my abstract and make a Cell-style graphical abstract.
On the right: the call your agent makes and the shape of the reply. No figure was generated for this example; the values in angle brackets are placeholders.
create_figure({
"description": "<the story of your abstract, in three or four stages>",
"kind": "graphical_abstract",
"style": "cell",
"aspect_ratio": "16:9"
})
{
"summary": "Figure ready: <image URL>. To change it, call edit_figure with figure_id \"<figure id>\".",
"extra": {
"figure_id": "<figure id>",
"status": "done",
"image_url": "<image URL>",
"credits_used": 20
},
"files": [
{
"name": "figure-<id>.jpg",
"url": "<image URL>",
"mimeType": "image/jpeg"
}
]
}What you get
- A landscape (16:9) graphical abstract as an image file
- Left-to-right story with clear arrows
- Editable through follow-up instructions
Good fit
- Submissions that require a graphical abstract
- Lab website and social posts
Not for
- Data plots and charts
Similar capabilities
Frequently asked questions
Your agent calls create_figure, get_figure over MCP with a description of the figure. ScholarMuse generates the image and returns a link to it. Figures usually take one to three minutes.
No. It costs 20 credits per figure, charged only when the call succeeds. A new account gets 50 credits once, valid for 30 days.
Claude, ChatGPT, Codex, Cursor, Gemini CLI and any other client that supports MCP.
Yes. The same tools (create_figure, get_figure) are available over the REST API.