figma_read_canvas
Reads the live, currently open Figma canvas as token-optimized JSX, tree, or JSON for direct inspection, avoiding custom tree-walk code.
Instructions
Read the LIVE, currently-open Figma document as token-optimized Pseudo-JSX/Tree/JSON — the same pipeline get_file/get_node use for the cloud API, applied to whatever is open in Figma Desktop right now. Prefer this over hand-writing a tree walk in figma_execute_code; it is far cheaper in tokens and its output format matches get_file/get_node exactly.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "figma_read_canvas"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Traversal depth from each requested node, hard-capped at 12 (default: 6). | |
| format | No | Output format — same meaning as get_file/get_node (default: 'jsx'). | |
| target | No | fileName of a specific connected Figma document, when more than one is open (see figma_list_targets). | |
| node_ids | No | Comma-separated node IDs to read. Omit to read the top-level frames of the current page. | |
| budget_tokens | No | Target response size in tokens (default: 4000). If the requested depth overshoots this, depth is reduced and re-serialized (no extra round trip) until it fits, with a trailing comment noting the reduction. | |
| include_hidden | No | Whether to include hidden (visible=false) layers (default: false). |