Skip to main content

Connecting over MCP

AR Clip exposes an MCP server, so a tool that speaks the Model Context Protocol can work on your project directly — reading the scene, adding objects, wiring events, writing patches.

The endpoint

https://<your-server>/api/mcp/v1

Authentication is a bearer token:

Authorization: Bearer <your-api-token>

Create the token in your account settings, under API & MCP.

Treat the token like a password

It can change your projects. Keep it out of anything you share, and revoke it if it leaks.

Scopes

A token carries only what you give it:

ScopeAllows
editor:readreading projects, scenes and resources
editor:writecreating and changing them
editor:aithe generation tools
editor:publishpublishing

Give a read-only token when you only want analysis. A model that cannot write cannot break anything, and a great deal of useful work — auditing a scene, explaining why something does not fire, planning changes — needs nothing more.

What connects

Anything implementing MCP over streamable HTTP. In practice: Claude Desktop, Claude Code, Cursor, and a growing number of editors. Each has its own place to declare a server — you give it the URL above and your token.

Working alongside the editor

Changes an assistant makes appear live in your editor, the same way a colleague's would, and they land in the collaboration history like any other edit.

So the productive shape is: keep the editor open on one screen, ask for changes, and watch them happen. You see immediately when something is not what you meant, instead of discovering it afterwards.

A session remembers which project and space you are working on, so you do not have to repeat it in every request.

What the tools cover

Grouped by what you would ask for:

AreaThe assistant can
Scenelist, create, move, parent, duplicate and delete objects
Componentsread and set any component on any object
Eventslist triggers and steps, add and edit events
Patchesread, write and validate node graphs, and preview the code they compile to
Animationauthor timeline presets
Physicsset bodies, colliders and starting velocities
Resourcesbrowse the project tree, create folders, import and generate assets
Interfaceread and write UI cards
Publishingpublish, with the right scope

Four more that are easy to miss, because they reach out of the server:

AlsoWhat it does
Screenshotscapture the viewport, so an assistant can look at what it built
Measurementan object's real bounding size in metres — how it checks scale
Scene exporttake a scene out as data
Blender bridgetalk to a running Blender: list objects, push a scene to it, pull one back
A screenshot is not proof

An assistant can see its own work, which helps — but a still frame says nothing about whether scripts run, whether physics settles, or whether a marker tracks. Those need a preview on a real device.

Several tools describe the platform to the model itself

list_component_schemas, list_event_types, list_patch_nodes and the describe_*_api tools answer from the live engine, so an assistant can look up exactly what exists rather than guessing from training data. If a model is inventing component names, tell it to call those first.

Ready-made tasks

The server also offers a few prompts an MCP client shows as commands:

PromptDoes
build-scenebuild a scene from a description
add-interactivitywire up taps, triggers and steps
animateput together a timeline
audit-scenelook for problems
prepare-publishcheck the things worth checking before publishing

Reading without changing

The server publishes its own reference as resources a client can read:

was://project/info        was://scene/current       was://scene/selection
was://scripting/api was://patch/api was://events/api
was://physics/api was://timeline/api was://resources/api
was://ui/api

These are generated from the engine, so they never describe a version of the platform that no longer exists.


Next: The assistant's skills