Make sure you have Node.js installed, as the MCP server requires it:
Copy
pip install praisonaiagents mcp
2
Set API Key
Set your OpenAI API key as an environment variable in your terminal:
Copy
export OPENAI_API_KEY=your_openai_api_key_here
3
Create a file
Create a new file puppeteer_agent.py with the following code:
Copy
from praisonaiagents import Agent, MCPimport os# Use a single string command with Puppeteer configurationpuppeteer_agent = Agent( instructions="""You are a helpful assistant that can automate web browser interactions. Use the available tools when relevant to perform web automation tasks.""", llm="gpt-4o-mini", tools=MCP("npx -y @modelcontextprotocol/server-puppeteer"))puppeteer_agent.start("Navigate to example.com and take a screenshot")
4
Run the Agent
Execute your script:
Copy
python puppeteer_agent.py
Requirements
Python 3.10 or higher
Node.js installed on your system
OpenAI API key (for the agent’s LLM)
Chrome or Chromium browser installed on your system