> For the complete documentation index, see [llms.txt](https://docs.rainbird.ai/rainbird/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rainbird.ai/rainbird/rae/connect-a-decision-model.md).

# Connect a decision model

Connect a decision model to your systems via the Model Context Protocol (MCP) or Application Programming Interface (API).

### The Connect area

The **Connect** area has two tabs:

* **MCP** provides the endpoint and configuration for agent clients.
* **API** provides the same decision model for direct API access with integration guidance.

{% hint style="success" %}
The MCP Server gives read-only access to query the decision model in that project. The MCP tools provide no build or edit capability and provides no access to other decision models.
{% endhint %}

### Choose your connection method

Choose **MCP** when you want an AI assistant or agent to discover and use the decision model in a conversation. It is usually the simplest option for business users configuring supported AI tools.&#x20;

Choose the **API** when developers need to call the decision model directly from an application or build a tailored user experience. Both use the same published decision model.

{% hint style="warning" %}
**Protect the endpoint address.** Anyone with the address can query the decision model. Those calls run against your Studio account. Pause the endpoint or rotate its address to stop existing access.
{% endhint %}


---

# 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.rainbird.ai/rainbird/rae/connect-a-decision-model.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.
