Gemini MCP Integration

Guide for integrating Google's Gemini models with PraisonAI agents using MCP

MCP(...) accepts three equivalent construction forms — see Three equivalent forms.

Add Gemini Tool to AI Agent

Quick Start

1. Set API Key

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

   export GOOGLE_API_KEY=your_google_api_key_here

2. Create a file

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

   from praisonaiagents import Agent, MCP
   import os
   
   # Get API key from environment variable
   google_api_key = os.environ.get("GOOGLE_API_KEY")
   
   search_agent = Agent(
       instructions="""You help book apartments on Airbnb.""",
       llm="gemini/gemini-2.5-pro-exp-03-25",
       tools=MCP(
           command="npx",
           args=["-y", "@openbnb/mcp-server-airbnb", "--ignore-robots-txt"],
           env={"GOOGLE_API_KEY": google_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 gemini_airbnb.py

Features