scene.read
Since 0.6
[editor or disk] The scene as canonical JSON (argus://contract/scene): the editor's document (unsaved edits too), else the file.
pointer: one value. id (* wildcard), tag, component: matching entities with their index, a row each when many; pointer then reads each. summary: counts, a large scene's answer unless full.
| Title | Read a scene |
| Mode | |
| Token cost | about 228 tokens (in the default list, paid on every call) |
| Toolset | core |
Arguments
| Argument | Type | Required | Default | Allowed values | Description |
|---|---|---|---|---|---|
component | string | no | |||
full | boolean | no | |||
id | string | no | |||
page | integer | no | |||
pointer | string | no | /entities/@door/transform: @x is the element whose id, else type, is x | ||
resolved | boolean | no | Prefabs expanded, project defaults merged, sources marked | ||
scene | string | no | The open scene when absent | ||
summary | boolean | no | |||
tag | string | no |
Example
An MCP tools/call with the required arguments (placeholders in angle brackets).
{
"name": "scene.read",
"arguments": {}
}