> For the complete documentation index, see [llms.txt](https://help.intangible.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.intangible.ai/intangible-mcp-agents/connect-muse.md).

# Meta Muse

Intangible works with Meta's Muse. The Muse app (Muse Spark) and Muse Code (Muse Wonder) build 3D scenes in Intangible over MCP. Apps, models and setup steps.

**Yes, Intangible works with Meta's Muse.** Muse drives Intangible from two places: the Muse app, and Muse Code in your terminal. Both build scenes.

## At a glance

| Meta app  | Where you add Intangible                                       | Sign-in                                   |
| --------- | -------------------------------------------------------------- | ----------------------------------------- |
| Muse app  | Ask Muse in Chat to connect to `https://mcp.intangible.ai/mcp` | **Approve access** on the link Muse sends |
| Muse Code | `~/.config/muse/settings.json`, under `mcpServers`             | `muse mcp login intangible`               |

## Apps and models

| Meta app  | Model                                                                                                  |
| --------- | ------------------------------------------------------------------------------------------------------ |
| Muse app  | Muse Spark                                                                                             |
| Muse Code | Muse Wonder (`muse-wonder-1.0`)                                                                        |
| Muse Code | Muse Wonder Full (`muse-wonder-full-1.0`): should work the same way if your Muse Code plan includes it |

## Before you start

* An Intangible account. Sign up at [studio.intangible.ai](https://studio.intangible.ai/?utm_source=help.intangible.ai\&utm_medium=docs\&utm_campaign=inline-link\&utm_content=connect-muse).
* A Meta account with access to the Muse app or Muse Code.
* For Muse Code: Muse Code installed, and a terminal.

## Set it up

The server URL is `https://mcp.intangible.ai/mcp`.

{% tabs %}
{% tab title="Muse app" %}

## Muse app: ask Muse to connect

The Muse app has no settings box for adding an MCP server. Muse sets the connection up itself when you ask:

> Connect to the Intangible MCP server at <https://mcp.intangible.ai/mcp>. It uses streamable HTTP and OAuth sign-in. Send me the sign-in link and I will approve it.

Open the link Muse sends and approve access on the Intangible page.

## Muse app: build a scene

Keep one Studio tab open, then [describe your first scene](/intangible-mcp-agents/intangible-mcp-agents.md#describe-your-first-scene). Muse builds, reads the scene back, and lists anything worth nudging by hand.
{% endtab %}

{% tab title="Muse Code" %}

## Muse Code: sign in

1. Install Muse Code from [dev.meta.ai](https://dev.meta.ai/products/muse-code).
2. Sign in with your Meta account:

   ```bash
   muse login
   ```
3. A browser page opens with a device code. Confirm the code matches the terminal and approve it.

## Muse Code: add the Intangible server

1. Open `~/.config/muse/settings.json` in a text editor. Create the file if it doesn't exist.
2. Add the `intangible` entry. The file needs `schema_version`, and servers go under `mcpServers`. If the file already has settings, keep them and add `intangible` alongside any other servers:

```json
{
  "schema_version": 1,
  "mcpServers": {
    "intangible": {
      "transport": "streamable_http",
      "url": "https://mcp.intangible.ai/mcp",
      "enabled": true,
      "mode": "optional"
    }
  }
}
```

3. Save the file, then sign in to Intangible:

   ```bash
   muse mcp login intangible
   ```
4. Click **Approve access** on the Intangible page that opens. The terminal prints `Logged in to MCP server intangible`.

## Muse Code: build a scene

1. Open a project in Studio at [studio.intangible.ai](https://studio.intangible.ai/?utm_source=help.intangible.ai\&utm_medium=docs\&utm_campaign=inline-link\&utm_content=connect-muse). Keep only that one Studio tab open.
2. Start `muse` in a terminal window.
3. Type `/model` and choose **muse-wonder-1.0**.
4. Ask it to use the intangible MCP server, then [describe your first scene](/intangible-mcp-agents/intangible-mcp-agents.md#describe-your-first-scene). Muse Code loads Intangible's orientation first, then builds.

Muse Wonder Full needs a Muse Code plan that includes it. If Muse Code says the model does not exist or you lack access, use `muse-wonder-1.0`.
{% endtab %}
{% endtabs %}

## Related

* [Agents & MCP](/intangible-mcp-agents/intangible-mcp-agents.md)
* [Choosing a model](/intangible-mcp-agents/choosing-a-model.md)
* [Troubleshooting and FAQ](/intangible-mcp-agents/troubleshooting-and-faq.md)

*Last updated 23 October 2026. Steps may change.*


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.intangible.ai/intangible-mcp-agents/connect-muse.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.