# JetBrains AI Assistant

JetBrains AI Assistant has native MCP client support built into all IntelliJ-platform IDEs (IntelliJ IDEA, PyCharm, WebStorm, GoLand, and others) since version 2025.2. No additional plugin is required.

## Prerequisites

* Any [<mark style="color:blue;">JetBrains IDE</mark>](https://www.jetbrains.com/products/) version 2025.2 or later with the AI Assistant feature enabled
* The `ionoscloud-mcp` binary built and available. For more information, see [<mark style="color:blue;">Quick Start</mark>](/cloud/ai/mcp-server/quick-start.md)
* An <code class="expression">space.vars.ionos\_cloud\_api</code> token. For least-privilege access, see [<mark style="color:blue;">Authentication</mark>](/cloud/ai/mcp-server/configuration/authentication.md#token-scope-by-product-area) to scope the token to only the tools you need.

## Add the MCP server

{% stepper %}
{% step %}

### Open MCP server settings

In your IDE, go to **Settings** (⌘ + , on macOS, Ctrl + Alt + S on Windows/Linux) > **AI Assistant** > **MCP Servers**.
{% endstep %}

{% step %}

### Add a new server

Select **+** (Add) and fill in:

* **Name:** `ionoscloud`
* **Command:** `/usr/local/bin/ionoscloud-mcp`
* **Environment variables:** Add `IONOS_TOKEN` with your API token value

To also enable Object Storage tools, add `IONOS_S3_ACCESS_KEY` and `IONOS_S3_SECRET_KEY` as additional environment variable entries.
{% endstep %}

{% step %}

### Enable the server

Toggle the server to **Enabled** and select **OK**.
{% endstep %}
{% endstepper %}

## Verify the connection

{% hint style="warning" %}
**Important:** MCP tools are only available in **Agent** mode. They are not available in Chat mode.
{% endhint %}

Open an AI Assistant chat, switch to **Agent** mode, and type: *List my* <code class="expression">space.vars.ionos\_cloud</code> *data centers.*

{% hint style="success" %}
**Result:** The assistant calls `list_datacenters` and returns your data centers.
{% endhint %}

{% hint style="info" %}
**Note:** All tools are registered at startup by default, so Compute Engine and Object Storage tools appear immediately. To reduce the startup tool count, add `IONOS_MCP_LOAD_MODE` with value `lazy` as an additional environment variable in the server settings, then call the `ionos_load_compute_tools` or `ionos_load_objectstorage_tools` sentinels on demand. For more information, see [<mark style="color:blue;">Selective Tool Loading</mark>](/cloud/ai/mcp-server/configuration/selective-tool-loading.md).
{% endhint %}

For full JetBrains MCP documentation, see [<mark style="color:blue;">Configure an MCP server</mark>](https://www.jetbrains.com/help/ai-assistant/configure-an-mcp-server.html) in the AI Assistant help.


---

# 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.ionos.com/cloud/ai/mcp-server/connect-to-an-ai-client/jetbrains.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.