Inspiration
I wanted to build a practical AI assistant that helps travelers decide what to wear and what to pack based on real weather conditions. Checking forecasts and planning clothing separately can take time, so I combined them into one assistant.
What it does
Alexa+ Weather & Packing Assistant provides current weather information and multi-day forecasts, recommends clothing based on forecast conditions, and generates travel packing checklists. Users interact through a Streamlit chat interface and can hear responses using offline text-to-speech.
How I built it
I built the application with Python and Streamlit. A local Ollama model (qwen3:8b) connects to a self-hosted Model Context Protocol (MCP) server. The MCP server exposes tools for weather retrieval, clothing suitability analysis, and packing checklist generation. The tools use Open-Meteo APIs for weather and geocoding data.
Challenges and learning
Building this project helped me understand how an AI model can use MCP tools to access live external data instead of relying only on its internal knowledge. I also learned how to connect a local language model, an MCP server, and a user interface into one application.
What's next
I would like to improve voice interaction, refine clothing recommendations, and make travel planning more personalized.
Built With
- mcp
- ollama
- open-meteo
- python
- pyttsx3
- streamlit
