> For the complete documentation index, see [llms.txt](https://docs.peakcommerce.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.peakcommerce.com/product/settings/access-security/ai-access.md). # AI Access **Settings → AI Access** is where you connect an AI assistant to your PeakCommerce tenant, and where you control whether it is allowed to connect at all. It uses the Model Context Protocol (MCP), the standard assistants like Claude use to reach outside tools. Nothing is connected by default. An assistant can reach your data only after an administrator enables access here. ## Your connection URL The page shows the address for **your** tenant — every tenant has its own — which you paste into an AI assistant that supports MCP connectors. **Copy** puts it on your clipboard. If your organization does not yet have a PeakCommerce hostname, there is no address to connect to and the page says so. A hostname is provisioned per tenant by PeakCommerce, so contact support rather than looking for a setting. ## Enabled or Disabled The badge beside the page title is the live state of the connector for your tenant: * **Enabled** — the URL accepts connections from people who sign in. * **Disabled** — the URL exists but refuses every connection. Nothing can reach your data. While access is off, the page still shows the URL, with a note that it will refuse connections. That is deliberate: you can hand the address to whoever will use it, and turn access on separately. ## How signing in works The assistant never receives a password or an API key. When someone connects, they are sent to **your own identity provider** to sign in, exactly as they would to reach PeakCommerce directly. The connection then acts as that person — and only that person. Two consequences worth knowing: * A connection can never do more than the person who authorized it already can. Their existing permissions still apply. * Someone who cannot sign in to your tenant cannot use the connector, whatever URL they hold. ## What a connected assistant can and cannot do The page lists both halves side by side. In summary, a connection **can** read and edit journeys, pages and their steps; read and edit product sets, business rules and native catalog products; and read personas, integrations and host routes. It **cannot** publish anything live — that is a separate permission a given connection may not hold, so an assistant may draft changes without being able to ship them. It also cannot read integration credentials or API keys, create or rotate API keys, or change users, roles and profiles. ## Who can see and change this Viewing this page requires the **AI Access** permission, which is separate from general settings access. That separation is deliberate: deciding whether an AI assistant may reach your journeys and catalog is a different decision from changing a display name, so it can be granted to a narrower set of administrators in your permission profiles. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.peakcommerce.com/product/settings/access-security/ai-access.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.