> For the complete documentation index, see [llms.txt](https://docs.mydbsync.com/cloud-workflow/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mydbsync.com/cloud-workflow/ai/model-context-protocol-mcp.md).

# Model Context Protocol (MCP)

MCP lets your chatbot use external tools to perform tasks instead of only providing text-based answers. The MCP connector is the main component that powers this integration.

You can add and manage these tools through a straightforward interface. To keep the chatbot efficient and prevent information overload, the system automatically identifies and loads only the most relevant tools for each user request.

With these tools, your chatbot can perform specific actions, such as the following:

* Retrieve organization IDs.
* Fetch subscription details.
* Troubleshoot account issues.
* Process or download error logs.

To configure the MCP, follow these steps:

{% stepper %}
{% step %}
Log in to DBSync with your credentials.
{% endstep %}

{% step %}
In the navigation pane, click <img src="/files/8AmM1JojwUsSd6EbaYBr" alt="" data-size="line"> (MCP).
{% endstep %}

{% step %}
On the **MCP Tools** page, click <img src="/files/qHHa4VnJo3i71DdbGsc6" alt="" data-size="line"> to display the **Tool Name** and **Description** for the available MCP servers.&#x20;

<div data-with-frame="true"><figure><img src="/files/sSQPPzA7xGekzwSO4y1V" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
Click **Test**.

* In the **Test MCP Discovery** dialog, enter a prompt in the field.&#x20;
* Click **Discover Tools**. The dialog displays a list of the tools that would be triggered by your prompt.
  {% endstep %}

{% step %}
Click **Add MCP Server**.
{% endstep %}

{% step %}
On the **Quick Setup** tab, for **Server URL**, enter the relevant URL.
{% endstep %}

{% step %}
For **Transport Type**, select from the provided options.<br>

<div data-with-frame="true"><figure><img src="/files/eBWOZBUReBo5RU0lWpYb" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
For **Authentication Type**, select from the provided options.<br>

<div data-with-frame="true"><figure><img src="/files/G8Yifbq44m91HVtahFnj" alt=""><figcaption></figcaption></figure></div>
{% endstep %}

{% step %}
For **Access Token**, enter your access token.
{% endstep %}

{% step %}
Click **Save Connection**.
{% endstep %}

{% step %}
Click **Test Connection**.
{% endstep %}

{% step %}
Verify that the tools load successfully. These tools can be used to perform a specific task by integrating them in [Chat Agent](/cloud-workflow/ai/chat-agents.md).
{% endstep %}
{% endstepper %}


---

# 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:

```
GET https://docs.mydbsync.com/cloud-workflow/ai/model-context-protocol-mcp.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.