Travel Assistant MCP Server
A production-ready MCP server for intelligent travel planning that integrates 16 tools, live APIs, and a gamification system to help users plan trips, track expenses, and discover events.
README
Travel Assistant MCP Server
A production-ready Model Context Protocol (MCP) server for intelligent travel planning.
It combines 16 powerful tools, live API integrations, database persistence, and a gamification systemβperfect for the Vibe Summer Challenge 2025.
π Live Deployment
| Endpoint | URL |
|---|---|
| MCP Server | https://travel-assistant-mcp.virtuosoofcoding633.workers.dev/mcp |
| Health Check | https://travel-assistant-mcp.virtuosoofcoding633.workers.dev/health |
β¨ Feature Highlights
- 16 MCP tools (weather, events, expenses, itinerary, gamification)
- Real APIs: FreeCurrencyAPI, Google Places, Open-Meteo, REST Countries
- Gamification: Points, levels, unlockable rewards
- Cloudflare Workers + D1 (SQLite) for serverless scale
- TypeScript + Hono.js + Drizzle ORM for type-safe development
- <7 ms average cold-start; sub-second responses
π Project Structure
travel-assistant-mcp/
βββ src/
β βββ index.ts # Worker entry
β βββ tools/ # 16 MCP tool handlers
β βββ db/ # Drizzle schema & migrations
β βββ lib/ # API helpers & gamification logic
βββ drizzle.config.ts
βββ wrangler.toml
βββ package.json
βββ .dev.vars.example
βββ README.md
π Quick Start
1. Clone & Install
git clone https://github.com/Virtuoso633/travel-assistant-mcp.git
cd travel-assistant-mcp
npm install
2. Environment Variables
cp .dev.vars.example .dev.vars
# Edit .dev.vars and add any API keys (optional β fallbacks provided)
3. Local Database & Dev Server
npm run db:generate # create drizzle client
npm run db:migrate # apply migrations locally
npm run dev # wrangler dev --local (http://localhost:8787)
4. Test Locally
curl -X POST http://localhost:8787/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
ποΈ Deploy to Cloudflare
Login & Deploy
npx wrangler login # OAuth or API token
npm run deploy # wrangler deploy
Remote Migration
npm run db:migrate:prod # applies migrations to D1 prod DB
π§ MCP Usage Examples
List Tools
curl -X POST https://travel-assistant-mcp.virtuosoofcoding633.workers.dev/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Create Itinerary
curl -X POST https://travel-assistant-mcp.virtuosoofcoding633.workers.dev/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc":"2.0",
"id":1,
"method":"tools/call",
"params":{
"name":"create_itinerary",
"arguments":{
"destination":"Kyoto, Japan",
"duration":3,
"startDate":"2025-09-15",
"interests":["culture","food"],
"budget":"mid-range",
"travelStyle":"solo",
"userId":"demo_user"
}
}
}'
π₯οΈ Claude Desktop Integration
- Create or edit:
~/.config/claude-desktop/claude_desktop_config.json - Add:
{ "mcpServers": { "travel-assistant": { "command": "npx", "args": ["@modelcontextprotocol/server-http", "https://travel-assistant-mcp.virtuosoofcoding633.workers.dev/mcp"] } } } - Restart Claude Desktop and use prompts like:
Plan a 5-day trip to Tokyo with a mid-range budget.
π API Reference (MCP)
tools/list
POST /mcp
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}
tools/call
POST /mcp
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "tool_name",
"arguments": { /* tool-specific */ }
}
}
π οΈ Scripts
npm run dev # local Cloudflare Worker
npm run deploy # deploy to Cloudflare
npm run db:generate # generate drizzle client
npm run db:migrate # migrate local DB
npm run db:migrate:prod # migrate prod D1
npm run test # MCP inspector
npm run lint # eslint
npm run type-check # TypeScript strict check
π€οΈ 16 MCP Tools (Quick List)
| Category | Tool | Description |
|---|---|---|
| Weather | get_weather |
5-day forecast |
compare_weather |
Compare two locations | |
| Events | find_events |
Google Places search |
save_event |
Save place to plan | |
get_saved_places |
List saved places | |
get_place_details |
Detailed place info | |
| Expenses | add_expense |
Track expense with FX |
convert_currency_live |
Live conversion | |
get_live_exchange_rates |
Multi-currency rates | |
get_expense_summary |
Totals & breakdown | |
| Itinerary | create_itinerary |
AI travel plan |
optimize_itinerary |
Route/time optimizer | |
get_user_itineraries |
List itineraries | |
get_itinerary_details |
Itinerary detail | |
| Gamification | get_user_progress |
Points/levels |
unlock_reward |
Redeem reward |
βοΈ Environment Variables (.dev.vars.example)
# ---------------- Required ----------------
DB_URL="file:./local.db"
# -------------- Optional Keys --------------
GOOGLE_MAPS_API_KEY=""
FREE_CURRENCY_API_KEY=""
BETTER_AUTH_SECRET=""
# -------------- Development ---------------
NODE_ENV="development"
DEBUG="true"
π Contributing
git checkout -b feature/amazing-feature
npm run lint && npm run type-check
git commit -m "Add amazing feature"
git push origin feature/amazing-feature
# open PR
π License
MIT β see LICENSE.
Built with β€οΈ for the Vibe Summer Challenge 2025
Demo Video URL :: https://drive.google.com/drive/folders/1_xjZcIVCSt5ZB9I2UmvN1YusxnDJO3pq?usp=sharing
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.