---
title: AI Travel Concierge - Multi-Agent MCP System
emoji: โ๏ธ
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: "5.9.1"
app_file: app.py
pinned: true
license: mit
tags:
- mcp-in-action-track-consumer
- mcp
- agents
- travel
- ai-assistant
- multi-agent
- gradio-6
- flux
- modal
- image-generation
short_description: "8 AI Agents plan your perfect trip with real booking links"
---
# โ๏ธ AI Travel Concierge - Multi-Agent MCP System
> **๐ MCP Hackathon Winter 2025 Submission**
> **Track 2: MCP in Action - Consumer Category**



**Your Personal AI Travel Planning Team** ๐
[โถ๏ธ Watch Demo Video](#demo-video) | [๐ Try Live Demo](https://huggingface.co/spaces/MCP-1st-Birthday/AI-Travel-Concierge)
---
## ๐ฏ What is AI Travel Concierge?
AI Travel Concierge is a **complete multi-agent AI system** that plans your entire trip using **8 specialized MCP servers** working together. Unlike simple chatbots, this system uses **autonomous AI agents** that:
- ๐ง **Reason & Plan** - Understands your travel preferences and creates personalized itineraries
- ๐ง **Use Real Tools** - Each agent has specialized tools via MCP (Model Context Protocol)
- ๐ **Generate Real Booking Links** - Every recommendation includes working links to Google Flights, Booking.com, Viator, and more
- ๐จ **Create Visual Content** - Generates custom AI travel posters using [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev) on Modal
---
## โจ Key Features
### ๐ค 8 Specialized AI Agents
| Agent | MCP Server | Capabilities |
|-------|------------|--------------|
| ๐ค๏ธ **Weather Agent** | `weather_server.py` | Real-time forecasts, best time to visit, packing suggestions |
| โ๏ธ **Flights Agent** | `flights_server.py` | Flight search with Google Flights & Skyscanner links |
| ๐จ **Hotels Agent** | `hotels_server.py` | Luxury hotel recommendations with Booking.com links |
| ๐ฏ **Activities Agent** | `activities_server.py` | Tours, attractions with Viator & GetYourGuide links |
| ๐ฝ๏ธ **Dining Agent** | `dining_server.py` | Restaurant recommendations with OpenTable links |
| ๐ **Transport Agent** | `transport_server.py` | Airport transfers, car rentals with real provider links |
| ๐งญ **Recommendations Agent** | `recommendations_server.py` | Smart destination finder for undecided travelers |
| ๐จ **Poster Agent** | `poster_server.py` | AI-generated travel posters via Modal [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev) |
### ๐ฏ Smart Destination Finder
**Don't know where to go?** Our intelligent recommendation system:
- Analyzes your interests (beach, adventure, culture, food, etc.)
- Considers your budget and travel dates
- Shows current deals and seasonal discounts
- Scores destinations to find your perfect match
### ๐ Premium Glass UI
- Beautiful dark mode glass-morphism design
- Mobile-responsive layout
- Real-time agent status indicators
- One-click quick destination buttons
### ๐ Real Booking Links
Every recommendation includes **working booking links**:
- โ๏ธ Google Flights & Skyscanner for flights
- ๐จ Booking.com & Hotels.com for accommodations
- ๐ซ Viator & GetYourGuide for activities
- ๐ฝ๏ธ TripAdvisor & OpenTable for restaurants
- ๐ Blacklane & Welcome Pickups for transfers
---
## ๐ ๏ธ Technical Architecture
```
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ GRADIO 6 FRONTEND โ
โ (Premium Glass UI + Chatbot) โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ
โผ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ AI ORCHESTRATOR (Qwen 235B) โ
โ Autonomous Planning, Reasoning, Execution โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโฌโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ MCP Protocol
โโโโโโโโโโโโโโโโโผโโโโโโโโโโโโโโโโ
โผ โผ โผ
โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ
โ Weather โ โ Flights โ โ Hotels โ
โ MCP โ โ MCP โ โ MCP โ
โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ
โ โ โ
โผ โผ โผ
โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ
โActivity โ โ Dining โ โTransportโ
โ MCP โ โ MCP โ โ MCP โ
โโโโโโโโโโโ โโโโโโโโโโโ โโโโโโโโโโโ
โ โ
โผ โผ
โโโโโโโโโโโ โโโโโโโโโโโ
โ Recom- โ โ Poster โ
โmendationโ โ MCP โโโโบ Modal FLUX.2-dev
โโโโโโโโโโโ โโโโโโโโโโโ
```
### Tech Stack
- **Frontend**: Gradio 6 with custom CSS (glass-morphism)
- **AI Model**: Qwen/Qwen3-235B-A22B-Instruct-2507 (Nebius)
- **MCP**: Model Context Protocol for tool integration
- **Image Gen**: Modal [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev) MCP for travel posters
- **Protocol**: Server-Sent Events (SSE) for real-time streaming
---
## ๐ Quick Start
### Try it Online
๐ [Launch AI Travel Concierge on Hugging Face Spaces](https://huggingface.co/spaces/ABDALLALSWAITI/AI-Travel-Concierge)
### Run Locally
```bash
# Clone the repository
git clone https://huggingface.co/spaces/ABDALLALSWAITI/AI-Travel-Concierge
# Install dependencies
pip install -r requirements.txt
# Set your API key
export NEBIUS_API_KEY="your-api-key"
# Run the app
python app.py
```
---
## ๐น Demo Video
> **[๐บ Watch Full Demo Video (YouTube Link)](#)**
>
> *Coming soon - 3-5 minute walkthrough showing:*
> - Natural language trip planning
> - All 8 agents in action
> - Real booking link generation
> - AI poster creation
> - Smart destination finder
---
## ๐ฎ How to Use
### Option 1: I Know Where I Want to Go
Simply type your trip request:
> *"Plan a romantic trip from New York to Paris for 2 people, December 15-22, moderate budget, interested in culture and food"*
The AI will automatically:
1. ๐ค๏ธ Check weather and best time to visit
2. โ๏ธ Find flight options with booking links
3. ๐จ Recommend hotels with prices and links
4. ๐ฏ Suggest activities and tours
5. ๐ฝ๏ธ Find the best restaurants
6. ๐ Arrange airport transfers
7. ๐จ Generate a custom travel poster!
### Option 2: Help Me Decide
Click **"๐ค Find My Perfect Destination"** and tell us:
- Your interests (beach, adventure, culture, etc.)
- Your budget range
- When you want to travel
We'll match you with the **perfect destinations** and show current deals!
---
## ๐ Project Structure
```
ai-travel-concierge/
โโโ app.py # Main Gradio application
โโโ weather_server.py # Weather MCP server
โโโ flights_server.py # Flights MCP server
โโโ hotels_server.py # Hotels MCP server
โโโ activities_server.py # Activities MCP server
โโโ dining_server.py # Dining MCP server
โโโ transport_server.py # Transport MCP server
โโโ recommendations_server.py # Smart recommendations MCP server
โโโ poster_server.py # AI poster generation MCP server
โโโ requirements.txt # Python dependencies
โโโ README.md # This file
```
---
## ๐ What Makes This Special?
| Feature | Traditional Chatbots | AI Travel Concierge |
|---------|---------------------|---------------------|
| Architecture | Single LLM | 8 Specialized MCP Agents |
| Tool Usage | Basic API calls | Full MCP Protocol |
| Booking Links | Generic or none | Real, working links |
| Personalization | Limited | Smart matching algorithm |
| Visual Output | Text only | AI-generated posters |
| Agent Autonomy | None | Full planning & reasoning |
---
## ๐จโ๐ป Team
**Solo Developer**: [@ABDALLALSWAITI](https://huggingface.co/ABDALLALSWAITI)
---
## ๐ฑ Social Media
> **[๐ฆ View on X/Twitter](#)** - *Link to social post*
>
> **[๐ผ View on LinkedIn](#)** - *Link to social post*
---
## ๐ Acknowledgments
- **Anthropic** - For creating MCP and co-hosting the hackathon
- **Gradio Team** - For Gradio 6 and organizing this amazing event
- **Nebius** - For providing Qwen API credits
- **Modal** - For Flux image generation MCP
---
## ๐จ The Flux Journey: From Training to Deployment
### Custom LoRA Training for This Hackathon
For this hackathon, I trained a custom **LoRA model specifically for travel posters** using [FLUX.1-Krea-dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev):
๐ **[Trip Poster LoRA Model on CivitAI](https://civitai.green/models/2146545/trip-poster)**
This LoRA was trained to generate professional travel agency style posters with:
- Bold destination typography
- Polaroid-style photo collages
- Travel-themed visual elements
- Professional marketing aesthetics
### Pivoting to FLUX.2-dev
Initially, I planned to use [FLUX.1-Krea-dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev) with my custom LoRA. However, when **[FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev)** was released with significant improvements, I decided to pivot and spent **2 days** deploying it on Modal instead.
### Deep Study: FLUX.2-dev Prompt Engineering for Tourism Posters
I conducted extensive research on FLUX.2-dev's prompt techniques to craft the perfect prompts for professional tourism posters. Key findings:
- **Structured prompt format** - FLUX.2-dev responds best to detailed, well-organized prompts
- **Style keywords** - Terms like "travel agency poster", "wanderlust aesthetic", "professional marketing" trigger the right visual style
- **Typography handling** - Specific instructions for bold destination text placement
- **Composition cues** - Polaroid collages, landmark silhouettes, gradient backgrounds
- **Color psychology** - Warm tones for beach destinations, cool tones for winter escapes
This prompt engineering research ensures the Poster Agent generates stunning, professional-quality travel posters every time.
I documented the entire deployment process:
๐ **[LinkedIn Post: Deploying Flux MCP on Modal](https://www.linkedin.com/posts/abdallah-issac_mcp-ai-machinelearning-activity-7400147561761697792-TFkL?utm_source=share&utm_medium=member_desktop&rcm=ACoAABflfdMBdk1lkzfz3zMDwvFhp3Iiz_I4vAw)**
๐ **[Complete Deployment Guide (GitHub Gist)](https://gist.github.com/al-swaiti/8ea1d7df6ab728d111406b70e26150be)**
The guide covers:
- Setting up Modal for GPU inference
- Deploying [FLUX.2-dev](https://huggingface.co/black-forest-labs/FLUX.2-dev) with optimal settings
- Creating an MCP server interface
- Integrating with Gradio applications
- Performance optimization tips
This enables the **Poster Agent** to generate stunning AI travel posters in ~30 seconds using H100 GPUs on Modal with the latest FLUX.2-dev model.
---
## ๐ License
MIT License - Feel free to use and modify!
---
**Built with โค๏ธ for the MCP Hackathon Winter 2025**
[](https://huggingface.co/spaces/ABDALLALSWAITI/AI-Travel-Concierge)