# Model Context Protocol

<figure><img src="/files/cQeLmAYcraxtrSPzd3Xf" alt=""><figcaption></figcaption></figure>

***

A key feature of the Hallway.ai embed is the ability to connect to your own **Model Context Protocol (MCP)** server.

In the Embed section of your dashboard, you can specify the URL of your custom MCP server. By doing this, you are directing the embed to use your own server for handling the chat interactions instead of the default Hallway.ai server.

This gives you complete control over the backend logic and allows for more advanced, customized functionality. The URL you provide must point to the specific directory where your MCP application is running, such as `https://your-server.com/mcp-endpoint`.

A starter kit is available on [GitHub](https://github.com/Hallway-Inc/mcp-starter) to help you get started with the protocol, it can be implemented in any programming language that conforms to the MCP standard.


---

# Agent Instructions: 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:

```
GET https://hallway.gitbook.io/embed/advanced/model-context-protocol.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.