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

# Mistral

> Learn how to build AI agents that integrate Mistral AI with Strata MCP servers to build AI agents that can interact with Gmail and Slack.

## Prerequisites

Before we begin, you'll need:

> [card] [Mistral API Key](https://console.mistral.ai/)
>
> Get your API key from Mistral AI Console

> [card] [Klavis AI API Key](https://klavis.ai/)
>
> Get your API key from Klavis AI

## Installation

First, install the required packages:

```bash Python theme={null}
pip install mistralai klavis
```

## Setup Environment Variables

```python Python theme={null}
import os

os.environ["MISTRAL_API_KEY"] = "YOUR_MISTRAL_API_KEY"  # Replace with your actual Mistral API key
os.environ["KLAVIS_API_KEY"] = "YOUR_KLAVIS_API_KEY"  # Replace with your actual Klavis API key
```

### Step 1 - Create Strata MCP Server with Gmail and Slack

```python Python theme={null}
from klavis import Klavis
from klavis.types import McpServerName, ToolFormat
import webbrowser

klavis_client = Klavis(api_key=os.getenv("KLAVIS_API_KEY"))

response = klavis_client.mcp_server.create_strata_server(
    servers=[McpServerName.GMAIL, McpServerName.SLACK], 
    user_id="1234"
)

# Handle OAuth authorization for each services
if response.oauth_urls:
    for server_name, oauth_url in response.oauth_urls.items():
        webbrowser.open(oauth_url)
        print(f"Or please open this URL to complete {server_name} OAuth authorization: {oauth_url}")
```

> [!NOTE]
>
> **OAuth Authorization Required**: The code above will open browser windows for each service. Click through the OAuth flow to authorize access to your accounts.

### Step 2 - Create method to use MCP Server with Mistral AI

This method handles multiple rounds of tool calls until a final response is ready, allowing the AI to chain tool executions for complex tasks.

```python Python theme={null}
import json
from mistralai import Mistral

def mistral_with_mcp_server(mcp_server_url: str, user_query: str):
    mistral_client = Mistral(api_key=os.getenv("MISTRAL_API_KEY"))

    messages = [
        {"role": "system", "content": "You are a helpful assistant. Use the available tools to answer the user's question."},
        {"role": "user", "content": user_query}
    ]

    mcp_server_tools = klavis_client.mcp_server.list_tools(
        server_url=mcp_server_url,
        format=ToolFormat.OPENAI
    )

    max_iterations = 20
    iteration = 0

    while iteration < max_iterations:
        iteration += 1

        response = mistral_client.chat.complete(
            model="mistral-small-latest",
            messages=messages,
            tools=mcp_server_tools.tools,
            tool_choice="auto"
        )

        assistant_message = response.choices[0].message
        messages.append(assistant_message)

        if assistant_message.tool_calls:
            for tool_call in assistant_message.tool_calls:
                tool_name = tool_call.function.name
                tool_args = json.loads(tool_call.function.arguments)

                print(f"🔧 Calling: {tool_name}, with args: {tool_args}")

                result = klavis_client.mcp_server.call_tools(
                    server_url=mcp_server_url,
                    tool_name=tool_name,
                    tool_args=tool_args
                )

                messages.append({
                    "role": "tool",
                    "name": tool_name,
                    "content": str(result),
                    "tool_call_id": tool_call.id
                })
        else:
            return assistant_message.content

    return "Max iterations reached without final response"
```

### Step 3 - Run!

```python Python theme={null}
result = mistral_with_mcp_server(
    mcp_server_url=response.strata_server_url,
    user_query="Check my latest 3 emails and summarize them in a Slack message to #general"
)

print(f"\n🤖 Final Response: {result}")
```

> [!TIP]
>
> Perfect! You've integrated Mistral AI with Klavis MCP servers.

## Next Steps

> [card] [Integrations](https://www.klavis.ai/docs/mcp-server/github.md)
>
> Explore available MCP servers

> [card] [API Reference](https://www.klavis.ai/docs/api-reference/introduction)
>
> REST endpoints and schemas

## Useful Resources

* [Mistral API Documentation](https://docs.mistral.ai/getting-started/quickstart)
* [MCP Protocol Specification](https://modelcontextprotocol.io/)

**Happy building with Mistral AI and Klavis** 🚀


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.