Google Drive MCP Integration

Guide for integrating Google Drive file management with PraisonAI agents using MCP

Add Google Drive Tool to AI Agent

Quick Start

1. Install Dependencies

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

   pip install praisonaiagents mcp
   
2. Set up Google Drive Credentials

   Set your Google Drive credentials path as an environment variable in your terminal:

   export GDRIVE_CREDENTIALS_PATH=path/to/your/gcp-oauth.keys.json
   export OPENAI_API_KEY=your_openai_api_key_here
   
3. Create a file

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

   from praisonaiagents import Agent, MCP
   import os
   
   # Get the credentials path from environment
   gdrive_credentials = os.getenv("GDRIVE_CREDENTIALS_PATH", "servers/gcp-oauth.keys.json")
   
   # Use a single string command with Google Drive configuration
   gdrive_agent = Agent(
       instructions="""You are a helpful assistant that can interact with Google Drive.
       Use the available tools when relevant to manage files and folders.""",
       llm="gpt-4o-mini",
       tools=MCP("npx -y @modelcontextprotocol/server-gdrive",
               env={"GDRIVE_CREDENTIALS_PATH": gdrive_credentials})
   )
   
   gdrive_agent.start("List files in my Google Drive")
   
4. Run the Agent

   Execute your script:

   python gdrive_agent.py
   

Requirements

• Python 3.10 or higher
• Node.js installed on your system
• Google Drive API credentials (OAuth keys)
• OpenAI API key (for the agent’s LLM)