3dCMS Knowledge Base
Open the editor
Drive from Claude (MCP)

Tools & quick phrases

What the MCP server lets Claude do — list, read, create, edit, and publish your scenes — and the phrases that trigger each tool.

Open in the interactive manual →

The interactive version has full-text search, a table of contents, and light/dark themes.


Once connected, Claude gains a small set of tools for working with your scenes:

ToolDoes
list_scenesList your saved scenes.
get_sceneRead a compact summary of one scene (nodes, transforms, materials).
create_sceneMake a new empty scene.
apply_opsApply a batch of edits — the same add/move/recolor/group operations as the in-editor Assistant, including placing point & spot lights, hanging cables (sagging power lines, ropes, festoon strings) between two points, the scatter op for set-dressing, and the make_page op below. One batch = one Undo.
get_scene_screenshotRender the scene server-side (real headless WebGL) and hand Claude an actual image of it — its "eyes" (see below).
publish_scenePublish to a public, shareable URL.
generate_3d / generate_materialGenerate assets (only when a fal key is set — paid).

Every result includes an editorUrl — open it while signed in to see and keep editing the scene in 3dCMS.

Quick phrases

Say……and Claude
"list my scenes"runs list_scenes
"make a scene called X with…"creates it and builds it
"in <scene>, add / move / recolor…"reads the scene, then edits it
"publish <scene>"gives you a public 3D link

Whole pages in one step

When you ask for a page — a heading, a paragraph, and a few navigation links — Claude uses the make_page composite op, which builds the entire page surface (hero heading, body paragraph, and clickable "sign" links) in a single operation instead of assembling it from a dozen primitives. It's faster and lays pages out consistently, so a multi-page site comes together in a handful of ops. You don't invoke it by name — just ask, e.g. "add a Contact page with a heading, a short intro, and a link back home."

Claude can see what it builds

Building a 3D scene blind is hard. With get_scene_screenshot, Claude renders your scene server-side with real WebGL and gets back an actual image — then judges it like an art director (floating objects? unreadable text? an empty horizon? bad spacing?) and fixes what's off with another apply_ops. It caps itself at a couple of look-and-fix rounds per request so it doesn't loop forever. The upshot: scenes come out looking intentional, not just structurally correct. (Heavy scenes can take a couple of minutes to render the first time; repeat shots are cached.)

Live scene lint

Every apply_ops result can carry advisory warnings — a lightweight scene lint that flags common mistakes like content with no ground or backdrop under it, "orphan" web blocks floating off a page, text that's too small to read, stacked duplicates, or an overcrowded page. The edits still apply; the warnings just tell Claude what to tidy up in its next batch. The same lint runs behind the in-editor Assistant, so guidance is identical wherever you build.

Big scenes? Build in batches. For large scenes, Claude works in batches of ~40–50 objects across several apply_ops calls, checking the scene (and a screenshot) between them. Try: "In my Gallery scene, add a row of five 1-meter cubes 2 m apart, then group them."
Spotted something off, or want a topic covered? Email buck.rackley@gmail.com.