Skip to content

Written by AI.How we work

Build1 publisherNot yet confirmed elsewhere3 min readPublished

Spline V2 turns the 3D editor into an endpoint, with the desktop app as the only door

A bundled MCP server lets Claude Code, Cursor, Codex and Antigravity edit live scenes. There is no headless option, and no documented way back from exported code into the source file.

The Engineer · Build desk

Drafted by a language model from the sources cited here and checked against its claim ledger before publication. How we use AISend a correction

What happened

  • Spline shipped V2 on Thursday, a full rebuild of its 3D editor that lets outside coding agents work directly on live, still-editable scenes.
  • The new Spline MCP Server exposes the editor to Claude Code, Cursor, Codex, Google Antigravity and VS Code.
  • That server ships inside the macOS and Windows desktop app; it does not run in the browser and there is no standalone package.
  • A prompt becomes structured MCP tool calls that Spline routes into an open editor tab and runs against the live document, creating a file if none is open.
  • Scenes still export to Vanilla JavaScript, Three.js, React, Next.js and React Three Fiber, using WebGPU with a WebGL fallback.

Compiled by The EngineerSomething wrong?How this is made

Why it matters

  • constraint Agent-driven 3D work cannot run unattended: every task needs a staffed machine with the application awake, which rules out build servers and overnight batches.
  • capability Design review can now happen after the agent instead of before the export, because what comes back is a document a designer can keep working in.
  • exposure A shared, collaborator-synced document is now reachable from a terminal prompt, so the blast radius of a careless instruction is the team's file rather than a local copy.
  • precedent Exposing the live editor over MCP, rather than improving the export format, becomes the expected move for creative tools; ElevenLabs has already done it to voice infrastructure.

The undo history is doing more work here than the MCP server is. Spline says every change an agent makes is treated as a normal editor operation, landing in the undo stack and syncing to everyone else in the file [1]. That puts the rollback path in the same place a designer already looks, which is a cheaper form of review than inspecting whatever an agent wrote to disk.

Getting there requires the app to insert itself into your tooling. When the desktop application starts, it scans for supported clients and writes the server into their configuration files; the developer then restarts the client and prompts normally [8]. Five clients are covered [17], and a single connection spans two surfaces, with Spline deciding whether a request is scene work for the 3D editor or interface work for Hana [14]. Convenient, and also a reminder that discovery is the vendor's call rather than the client's.

The asymmetry is on the way out. Spline's runtime API can control a published scene, but the company documents no path for changes made in exported code to flow back into the original 3D file; an agent that needs to revise the source has to return through MCP and work in the live editor [2]. Set that against the packaging and you are left with one writable entrance to the source of truth, which is an MCP call executed against an open tab on somebody's desktop [16]. Anything an agent edits after export is a branch with no merge.

Hana's half of the round trip is narrower than it sounds. The agent can turn an existing component into an editable frame and carry visual changes back into application code, using stable references on exported elements to find the right place in the source [12]. Hana supports only a subset of HTML and CSS built around flexbox, though, so complex markup and framework-specific components have to be reconciled with the existing code rather than replaced outright [13]. Reconciliation is human work, and it is where the closed loop between design file and repository actually leaks.

Spline already ships its own agent that will build and edit a scene from a prompt [3], so the pitch for MCP is not that a model can produce 3D. It is that the coding agent already holds the codebase and the work in progress, and nobody wants to rebuild that context in a separate Spline conversation [c2b]. That is an argument about where context should live, and it has a consequence the marketing does not mention: the context stays in the client, while the artefact stays in Spline, and only Spline's application can carry a write between them.

What to watch

  • Whether Spline ships an MCP server that runs without the desktop application open on a workstation.
  • Whether a documented route appears for edits made in exported code to return to the original 3D file.
  • Whether Hana's HTML and CSS coverage grows past its flexbox subset, which is where the design-to-repo round trip currently needs hand reconciliation.
Loading claim ledger
Loading source directory links
Loading share composer
Loading topic controls
Loading related stories