Skip to main content
Planning a trip requires pulling together information from multiple sources: flights, hotels, weather, attractions, local tips. An agent with access to search and weather APIs can handle this coordination. This example combines web search for travel information with a weather API for forecast data. The agent builds a coherent travel plan from these sources. 
import asyncio
from dedalus_labs import AsyncDedalus, DedalusRunner
from dotenv import load_dotenv

load_dotenv()

async def main():
    client = AsyncDedalus()
    runner = DedalusRunner(client)

    result = await runner.run(
        input="""I'm planning a 5-day trip to Paris from New York in October.
        Budget: $3000. Mid-range accommodations preferred.
        
        Help me find:
        1. Flight options and approximate prices
        2. Hotel recommendations in central Paris
        3. Weather forecast for October
        4. Must-see attractions and restaurant suggestions
        5. Practical travel tips""",
        model="openai/gpt-4o-mini",
        mcp_servers=[
            "joerup/exa-mcp",
            "tsion/brave-search-mcp",
            "joerup/open-meteo-mcp"
        ]
    )

    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())

​
MCP Servers Used

ServerPurpose
joerup/exa-mcpSemantic search for travel content
tsion/brave-search-mcpCurrent prices, availability, reviews
joerup/open-meteo-mcpWeather forecasts

​
Why This Works

The agent synthesizes across domains. Weather affects what to pack. Budget constraints filter hotels and dining. You get a coherent plan instead of scattered facts. This pattern extends to any planning task that pulls from multiple sources: event planning, relocation research, project scoping.