# Dust

[**Dust**](https://dust.tt/) is a platform to build, deploy, and run AI agents that connect to your internal tools and data sources.\
It’s especially useful for teams building AI copilots for sales, support, or operations — letting you combine LLMs with APIs, knowledge bases, and business context.

## Pre-requisite 

* You have a MadKudu API key. Refer to [this article](/getting-started/quickstart.md) to get your API key. 
* You are a Dust admin. 

## Add MadKudu MCP as a Connection to your space

1. Go to **Spaces > Tools**, click **+ Add Tools,** then **+ Add MCP Server**

<figure><img src="/files/BaxAlya6Viz2mAMdQj2N" alt=""><figcaption></figcaption></figure>

2. Enter the **URL** below **-** Don't forget to replace the API key in the URL.&#x20;

```bash
https://mcp.madkudu.com/YOUR_API_KEY/mcp
```

No need for a Bearer token&#x20;

<figure><img src="/files/GLZ7ACfP0X4DlBhgURay" alt=""><figcaption></figcaption></figure>

3. Click **Save**

You'll now see the different tools available in the right panel

Follow the official[ Dust documentation ](https://docs.dust.tt/docs/managing-datasources)for more information


---

# 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://developers.madkudu.com/madkudu-mcp/install-in-ai-platforms-in-2min/dust.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.