> ## Documentation Index
> Fetch the complete documentation index at: https://docs.activeviam.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How Atoti connects with LLMs

> How Atoti Intelligence connects to external LLMs using Spring AI, covering the two integration modes: direct LLM configuration for Atoti UI and the Atoti MCP Server bridge for third-party tools such as Claude Desktop and ChatGPT.

## Why does Atoti Intelligence need an LLM?

Atoti Intelligence does not include its own internal large language model (LLM), so clients connect the LLM of their
choice.
This ensures:

* No vendor lock‑in
* On‑prem, cloud, or custom LLM flexibility
* Full control over data privacy and model selection

An LLM enables Atoti Intelligence to:

* Analyze data and generate clear explanations
* Understand user queries in natural language
* Create visualizations based on context
* Provide smart, conversational assistance

## Which LLM providers are supported?

Atoti Intelligence works with any LLM supported by **Spring AI**.

Configuration guides are provided for:

* Amazon Bedrock
* OpenAI

## How does Atoti communicate with an LLM?

There are two ways to create a bridge between Atoti and an LLM.
The choice depends on where Atoti Intelligence is used:

1. Atoti UI is used to interact with Atoti Intelligence
2. A third party application (Claude, ChatGPT, etc.) is used to interact with Atoti Intelligence.

Keep in mind that Auto-Explain and Visualize This can only be used from inside an Atoti UI dashboard.
They are not available when interacting with Atoti from a third party application.

### How to configure an LLM for use in Atoti UI

This provides the full native AI experience.

#### Configure an LLM

1. Connect Atoti UI to your Atoti application.
2. Configure the external LLM you want to use.
3. The user can interact with Atoti Intelligence inside Atoti UI.

<Frame>
  <img src="https://mintcdn.com/activeviam/J0McnvoVg4x05kNG/atoti-intelligence/6.1/images/atoti-intelligence-llm.png?fit=max&auto=format&n=J0McnvoVg4x05kNG&q=85&s=1bc2b5230dbf8e18b27aa43849b1f525" alt="atoti-intelligence-llm.png" width="2008" height="1380" data-path="atoti-intelligence/6.1/images/atoti-intelligence-llm.png" />
</Frame>

### How to connect an LLM to Atoti using the Atoti MCP server

Some teams prefer external AI tools such as Claude Desktop, IDE assistants, or custom agent platforms.\
This mode uses the **Atoti MCP server**.

The Atoti Model Context Protocol (MCP) server is a lightweight service that exposes Atoti’s analytical capabilities to
external LLMs.
It acts as a bridge between your Atoti data model and an external LLM‑powered tool.

#### What does the MCP server provide?

* Exposure of Atoti tools to LLM clients such as Claude
* Dynamic interaction with Atoti cubes, hierarchies, and measures
* Custom extensions for business‑specific logic
* A standardized, vendor‑agnostic integration protocol

#### Connect an LLM to the Atoti MCP server

1. The third party tool is automatically connected to an LLM.
2. Use Atoti MCP server to connect the LLM to Atoti
3. The user can interact with Atoti Intelligence inside the third party tool.

<Frame>
  <img src="https://mintcdn.com/activeviam/J0McnvoVg4x05kNG/atoti-intelligence/6.1/images/atoti-intelligence-connect-mcp.png?fit=max&auto=format&n=J0McnvoVg4x05kNG&q=85&s=d9a08e4a1f93e124909126d5da89617b" alt="atoti-intelligence-mcp.png" width="1928" height="1380" data-path="atoti-intelligence/6.1/images/atoti-intelligence-connect-mcp.png" />
</Frame>

## Related reading

Find out how to

* [Configure an LLM for Atoti with Atoti Java SDK](../developer-guide/enable-ai-tools/atoti-java-sdk/llm-set-up/llm-config)
* [Learn more about MCP server](../developer-guide/mcp-server/introduction)