# Using AI & the Academy Shade MCP

Connect the Academy Shade MCP to any MCP-compatible client with this server URL:

`https://academy.shade.inc/~gitbook/mcp`

If your client supports remote MCP servers, setup usually takes less than a minute.

### Quick dropdown

You can add the MCP or copy context directly from the docs.

<figure><img src="/files/LA81bpo5cSxewLhTUbZe" alt=""><figcaption></figcaption></figure>

### Add it to your client

{% hint style="info" %}
Different clients use different names. You may see **MCP server**, **connector**, **tool**, or **integration**. The flow is the same.
{% endhint %}

{% tabs %}
{% tab title="Claude" %}

1. Open Claude's **Settings**.
2. Find the **MCP**, **Tools**, or **Integrations** area.
3. Add a new server.
4. Name it **Academy Shade**.
5. Paste this URL:

   `https://academy.shade.inc/~gitbook/mcp`
6. Save the server.
7. Refresh Claude if needed.
8. Test it with:
   * `How do I set up a workspace in Shade?`
   * `What is the difference between guests and members?`
     {% endtab %}

{% tab title="Cursor" %}

1. Open Cursor **Settings**.
2. Go to the **MCP** or **Tools** section.
3. Add a new MCP server.
4. Name it **Academy Shade**.
5. Paste this URL:

   `https://academy.shade.inc/~gitbook/mcp`
6. Save the server.
7. Refresh Cursor if needed.
8. Use it from chat or agent mode with a prompt like:
   * `How does ShadeFS caching work?`
   * `How do I invite a guest into Shade?`
     {% endtab %}

{% tab title="ChatGPT / Codex" %}

1. Open your **Tools**, **Connectors**, or **MCP** settings.
2. Add a custom server if that option is available.
3. Name it **Academy Shade**.
4. Paste this URL:

   `https://academy.shade.inc/~gitbook/mcp`
5. Save the server.
6. Refresh the session if needed.
7. Test it with:
   * `How do permissions work in Shade?`
   * `How do I mount a drive in ShadeFS?`

If your ChatGPT or Codex environment does not expose custom MCP servers yet, use the Academy Shade MCP through Claude, Cursor, or another MCP-compatible client instead.
{% endtab %}

{% tab title="VS Code" %}

1. Open the MCP-compatible extension you use in VS Code.
2. Go to that extension's **MCP** or **Server** settings.
3. Add a new remote server.
4. Name it **Academy Shade**.
5. Paste this URL:

   `https://academy.shade.inc/~gitbook/mcp`
6. If prompted for transport, use the standard remote HTTP option the extension recommends.
7. Save the configuration.
8. Reload VS Code or restart the extension if needed.
9. Test it with:
   * `How do I create a BYOS drive in Shade?`
   * `How do comments work on assets?`
     {% endtab %}

{% tab title="Other MCP clients" %}

1. Open your client's **MCP**, **Tools**, or **Connectors** settings.
2. Add a new remote server.
3. Name it **Academy Shade**.
4. Paste this URL:

   `https://academy.shade.inc/~gitbook/mcp`
5. Save the configuration.
6. Refresh the client if needed.
7. Test it with:
   * `How do I search with AI in Shade?`
   * `What is the difference between guests and workspace members?`
     {% endtab %}
     {% endtabs %}

### What to expect after connecting

Once connected, your assistant can help with:

* Shade onboarding
* Workspace and permission questions
* ShadeFS setup and troubleshooting

It is best for product guidance, workflows, and docs lookups.

### Troubleshooting

If the server does not appear:

* Confirm the URL is exactly `https://academy.shade.inc/~gitbook/mcp`
* Refresh or fully restart the client
* Make sure your client supports remote MCP servers

If your client only supports local MCP servers, use an MCP-compatible client that supports remote servers instead.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://academy.shade.inc/using-ai-and-the-academy-shade-mcp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.