generate_svg
Create editable SVG icons, logos, illustrations, and diagrams from text prompts, placing them on the canvas as native shapes for scalable, easily modified designs.
Instructions
Generate editable vector graphics (SVG) from a text prompt and place them on the canvas as native editable shapes. Use for icons, logos, illustrations, diagrams — anything that should stay crisp and remain editable. For photos / realistic images use generate_image instead. Optional referenceElementIds (up to 4) export to PNG and steer style. Use n (1–4) for parallel variations of a single prompt, or targets to fan out distinct prompts in parallel. Call get_knowledge(["svg/prompts","svg/integration"]) for prompt patterns and decision rules. Requires Quiver API key.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"canvasId": "<canvasId>"
},
"name": "generate_svg"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | Number of variations from the single prompt (1–4, default 1). Cheaper than `targets` because it is one API call. | |
| intent | No | A short present-tense line shown beside your cursor while the vector is drawn, e.g. 'Sketching a fox logo'. Optional; derived from the prompt when absent. | |
| prompt | No | Natural-language description of the SVG to generate. | |
| targets | No | Batch mode: distinct prompts generated in parallel. Use for multiple different SVGs (e.g. "search icon", "settings icon"). | |
| canvasId | Yes | Canvas ID. Required. | |
| sessionId | No | Session ID for per-session visual feedback. Optional. | |
| instructions | No | Optional style/behavior instructions for the model. | |
| referenceElementIds | No | Element IDs to export as PNG and pass as style references (up to 4). |