Mistral MCP Integration

Guide for integrating Mistral models with PraisonAI agents using MCP

Add Mistral Tool to AI Agent

Quick Start

1. Set API Key

   Set your Mistral API key as an environment variable in your terminal:

   export MISTRAL_API_KEY=your_mistral_api_key_here
   
2. Create a file

   Create a new file mistral_airbnb.py with the following code:

   from praisonaiagents import Agent, MCP
   import os
   
   # Get API key from environment variable
   mistral_api_key = os.environ.get("MISTRAL_API_KEY")
   
   search_agent = Agent(
       instructions="""You help book apartments on Airbnb.""",
       llm="mistral/mistral-large-latest",
       tools=MCP(
           command="npx",
           args=["-y", "@openbnb/mcp-server-airbnb", "--ignore-robots-txt"],
           env={"MISTRAL_API_KEY": mistral_api_key}
       )
   )
   
   search_agent.start("MUST USE airbnb_search Tool to Search. Search for Apartments in Paris for 2 nights. 04/28 - 04/30 for 2 adults. All Your Preference")
   
3. Install Dependencies

   Make sure you have Node.js installed, as the MCP server requires it:

   pip install "praisonaiagents[llm]"
   
4. Run the Agent

   Execute your script:

   python mistral_airbnb.py
   

Requirements

• Python 3.10 or higher
• Node.js installed on your system
• Mistral API key

Features

Mistral Large

Leverage Mistral’s powerful large language model.

MCP Integration

Seamless integration with Model Context Protocol.

Airbnb Search

Search for accommodations on Airbnb with natural language queries.

Environment Variables

Securely pass API keys using environment variables.