> For the complete documentation index, see [llms.txt](https://docs.intelligems.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.intelligems.io/developer-resources/mcp-server.md).

# MCP Server

The Intelligems MCP (Model Context Protocol) Server provides AI assistants like Claude, ChatGPT, and Gemini with secure, authenticated access to your Intelligems data and Shopify store information through a standardized protocol.

## What is MCP?

The Model Context Protocol (MCP) is an open standard created by Anthropic that allows AI assistants to securely connect to external data sources and tools. The Intelligems MCP Server implements this protocol to give AI assistants controlled access to:

* Your Intelligems experiments and experiences
* Organization configuration
* Shopify store catalog, collections, and pages
* Analytics and audience data
* Custom events and integrations

## Prerequisites

* An active Intelligems account
* A Shopify store connected to Intelligems
* An MCP-compatible AI client (e.g., Claude Desktop, ChatGPT, Gemini, etc.)

## Installation

The Intelligems MCP Server is hosted at: `https://ai.intelligems.io`

No installation is required - the server is hosted by Intelligems and ready to use.

## Configuration

Add the Intelligems MCP Server to your AI client's configuration following the applicable guide linked below:

1. [Claude (Desktop & Code)](/developer-resources/mcp-server/claude.md)
2. [Google Gemini](/developer-resources/mcp-server/google-gemini.md)
3. [ChatGPT](/developer-resources/mcp-server/chatgpt.md)
4. [Grok](https://docs.intelligems.io/developer-resources/mcp-server/grok)

### **Built-in skills**

The Intelligems MCP comes with seven built-in skills. They run automatically when you ask a related question, so you don't need a slash command. Each one reads your store's data, recommends what to run, and builds it as a draft for you to review.

To see what's available on your plan, ask "What can Intelligems do for my store?" Some skills depend on the modules on your plan.

See the full list on the [Intelligems MCP page](https://www.intelligems.io/mcp).

#### **Other MCP Clients:**

Refer to your client's documentation for adding OAuth2-authenticated SSE-based or http MCP servers.

* HTTP: `https://ai.intelligems.io/mcp` (recommended)
* SSE: `https://ai.intelligems.io/mcp/sse`

## Multi-Organization Support

If you have access to multiple Intelligems organizations, you can specify which one to use:

* During initial authentication, choose any organization installed on Intelligems. This is only used for authentication.
* Most tools accept an optional `organization` parameter to override the default
* Use the `getOrganizationsList` tool to see all organizations you have access to
* If you would like to always use a specific organization, add a System Prompt or Custom Instruction to your LLM with these details.


---

# 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://docs.intelligems.io/developer-resources/mcp-server.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.