> For the complete documentation index, see [llms.txt](https://wiki.crosswatch.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wiki.crosswatch.app/crosswatch/settings/ui-settings/ai-help.md).

# AI Help

Use AI to diagnose CrossWatch from the built-in assistant or your own MCP app.

Use AI to inspect and diagnose your CrossWatch installation.

Both options inspect CrossWatch through read-only tools. The built-in assistant can also suggest action cards, such as running a pair or creating a backup. Nothing runs until you select **Run** on a card. The MCP connection remains read-only.

### Choose an option

#### Ask CrossWatch

Use the built-in assistant in the CrossWatch web UI. Connect a cloud or local model, then ask about syncs, scrobbling, connections, backups, Tracker, playlists, Continue watching or maintenance. New setups have Google Gemini and a model prefilled; add your API key and select **Save and turn on**.

It sends only the diagnostic data needed for an answer. Sources are shown with every response.

{% content-ref url="/pages/TZTWdjcYRKDjQ5PHE5pS" %}
[Assistant](https://wiki.crosswatch.app/crosswatch/settings/ui-settings/ai-help/assistant.md)
{% endcontent-ref %}

#### Connect your own AI app

Connect an MCP-compatible AI app on your computer to CrossWatch. Create a read-only token, then let the app inspect health, logs, events, pairs, and settings.

This is useful when you prefer an existing AI development tool or desktop app.

{% content-ref url="/pages/26dSjpHe83HJDvB5xhdr" %}
[MCP Connect AI](https://wiki.crosswatch.app/crosswatch/settings/ui-settings/ai-help/mcp-connect-ai.md)
{% endcontent-ref %}

### Privacy and security

CrossWatch removes secrets before sharing diagnostic data. This includes passwords, API keys, tokens, webhook addresses, and sign-in settings.

Cloud models receive diagnostic data needed to answer your question. Local models keep that data on your network. Audit events are never available.


---

# 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://wiki.crosswatch.app/crosswatch/settings/ui-settings/ai-help.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.
