Everything an AI assistant can read or change through the connector, by area.
The connector exposes a little over a hundred operations, grouped by what they act on. Roughly two fifths only read; the rest can change something, and those are the ones the write permission gates.
| Area | Covers |
|---|---|
| Pages | The biggest surface by far: listing, rotating, clipping, renaming, renumbering, importing, placing, comparing, scale, titles and page context. |
| Utilities | Systems, stages, pipes, structures, runs and references. |
| Materials | Items, sub-items, layers and quantities. |
| Markup | Listing, creating, updating and deleting annotations, and holes. |
| Groups and collections | Page groups and collections: creating, assigning, merging. |
| Project | The project map and summary, plus a project memory it can write notes into. |
| Documents | Reading documents: outline, sections, requirements, and querying them. |
| Spatial | Measuring, resolving a sheet, snapping a line, and the vectors inside a region. |
| Vectors and text | The drawing's own geometry and text: searching, extracting a region, layer lists. |
| Scale | Setting, calibrating and auditing page scales. |
| View | Navigating and capturing the canvas. |
The useful question is not which tools exist but what they add up to: