# TripWeaver: MCP-Based Multi-Agent Travel Planner

TripWeaver is a multi-agent travel planning application that combines FastAPI, Gradio, LangGraph, and MCP tools to help users search hotels, flights, and plan trips.

## Features
- Multi-agent travel planning workflow
- Streaming backend responses
- Gradio-based chat interface
- MCP tool endpoints for hotel and flight actions

## Tech Stack
- Python
- FastAPI
- Gradio
- LangGraph
- MCP

## Run locally

1. Create and activate a virtual environment
   ```bash
   python -m venv .venv
   .venv\Scripts\activate
   ```
2. Install dependencies
   ```bash
   pip install -r requirements.txt
   ```
3. Start the backend
   ```bash
   python main.py
   ```
4. Start the MCP server
   ```bash
   python mcp_travel_server.py
   ```
5. Start the frontend
   ```bash
   python frontend.py
   ```

## Project structure
- main.py: FastAPI streaming backend
- mcp_travel_server.py: MCP tool server
- frontend.py: Gradio UI
- agents/: orchestration and tool agents