> For the complete documentation index, see [llms.txt](https://help.pagefly.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.pagefly.io/integrations/ai-assistant-connector.md).

# AI Assistant Connector

Use Claude, ChatGPT or another AI assistant to read, build and publish your PageFly pages.

The **AI assistant connector** lets an AI assistant you already use — Claude, ChatGPT or any client that supports MCP connectors — work with your PageFly pages from its own chat: list and inspect pages, search templates, read Page Checkup and A/B results, build a new page section by section, preview it in your theme and publish it when you say so.

It uses the open **Model Context Protocol (MCP)**. You approve every connection inside PageFly, in your Shopify admin, and can disconnect at any time from **Preferences → Account**.

### In this section

* [Connect PageFly to Claude, ChatGPT or another AI assistant](/integrations/ai-assistant-connector/connect-pagefly-to-claude-chatgpt-or-another-ai-assistant.md) — requirements, step-by-step setup per assistant, how building works, troubleshooting.
* [What your AI assistant can do](/integrations/ai-assistant-connector/what-your-ai-assistant-can-do.md) — the full list of what it can build, edit, check, measure and publish, and what it deliberately cannot.
* [Data, permissions and security](/integrations/ai-assistant-connector/ai-assistant-connector-data-permissions-and-security.md) — what the assistant can and cannot access, how access is granted and revoked, where your data goes.


---

# 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.pagefly.io/integrations/ai-assistant-connector.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.