TravelMind AI MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TravelMind AI MCP ServerPlan a 5-day trip to Tokyo from San Francisco with a $2000 budget."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
โ TravelMind AI โ Real-Time Agentic Travel Planner
A multi-agent AI travel planner powered by Google Serper API (live Google search) and an MCP Server (Model Context Protocol). Four specialized agents collaborate in a pipeline to produce a complete, real-time travel plan.
๐ค Agent Architecture
User Input
โ
โผ
AgentOrchestrator
โ
โโโ Phase 1 โโ SearchAgent โโโโโโโโโโโโโโโโโโโโ Google Serper API
โ Fires 10 concurrent live searches:
โ flights ยท hotels ยท attractions ยท weather ยท visa
โ food ยท safety ยท budget ยท return flights ยท news
โ
โโโ Phase 2 (parallel) โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ โโโ PlanningAgent โ synthesises search results into travel info
โ โ (visa, safety, weather, attractions, news)
โ โโโ BudgetAgent โ extracts real prices from Serper snippets,
โ builds full cost breakdown
โ
โโโ Phase 3 โโ ItineraryAgent โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Builds day-by-day plan from live Serper places data
AI-generated (if Gemini key) or rule-based fallbackRelated MCP server: trip-planner-mcp
๐ MCP Server
The MCP server exposes all agent tools as JSON-RPC 2.0 endpoints.
Endpoint | Method | Description |
| POST | JSON-RPC 2.0 tool dispatcher |
| GET | List all 18 registered tools |
| GET | Health check & status |
| GET | SSE stream โ real-time agent events |
Registered Tools (18)
Tool | Description |
| Live flight search between two cities |
| Hotels with live prices and ratings |
| Top tourist attractions at destination |
| Current and forecast weather |
| Visa requirements by nationality |
| Restaurants and dining options |
| Travel safety advisories |
| Daily cost and expense estimates |
| General Google search for any travel query |
| Targeted train fares and duration search |
| Targeted restaurant and cuisine search |
| Targeted attraction hours and ticket search |
| Targeted route travel-time search |
| Structured category budget calculation |
| Transparent caller-rate currency conversion |
| Run the full 4-agent pipeline, returns full plan |
| Day-by-day itinerary from live data |
| Detailed budget calculation |
๐ Quick Start
1. Install
npm install2. Configure
cp .env.example .env
# Edit .env โ add your Serper API key (required for live data)Get your free Serper API key at serper.dev โ 2,500 free searches/month.
3. Run
# Interactive CLI planner
npm start
# MCP server only (for integrations)
npm run mcp
# Browser trip planner
# Start the MCP server, then open http://localhost:3001
# Run verification tests
npm run verify๐ API Keys
Key | Required? | Where to get | Free tier |
| โ Yes | 2,500 searches/mo | |
| โ No | Free tier |
Without Serper: App runs in estimation mode with built-in data.
Without Gemini: Uses rule-based itinerary and snippet extraction (fully functional).
๐ก MCP Server API โ Example Calls
Health check
curl http://localhost:3001/mcp/healthList tools
curl http://localhost:3001/mcp/toolsCall a tool (JSON-RPC 2.0)
curl -X POST http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": "1",
"method": "tools/call",
"params": {
"name": "search_flights",
"arguments": {
"origin": "New York",
"destination": "Bangkok",
"date": "2026-11-15"
}
}
}'Plan a full trip via MCP
curl -X POST http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": "2",
"method": "tools/call",
"params": {
"name": "plan_full_trip",
"arguments": {
"origin": "London",
"destination": "Tokyo",
"startDate": "2026-12-01",
"endDate": "2026-12-10",
"numTravelers": 2,
"totalBudget": 5000,
"currency": "USD",
"budgetTier": "moderate",
"travelType": "cultural",
"nationality": "GB"
}
}
}'SSE event stream
curl -N http://localhost:3001/mcp/events๐ Project Structure
Travel_planner_agent/
โโโ src/
โ โโโ main.js # Entry point
โ โโโ agents/
โ โ โโโ SearchAgent.js # Fires all Serper searches
โ โ โโโ PlanningAgent.js # Synthesises search โ travel info
โ โ โโโ RealtimeBudgetAgent.js # Real-time price extraction & budget
โ โ โโโ RealtimeItineraryAgent.js # Day-by-day plan from live places
โ โ โโโ BaseAgent.js # (shared base)
โ โ โโโ TransportationAgent.js # (legacy, used by fallback pipeline)
โ โ โโโ AccommodationAgent.js
โ โ โโโ BudgetAgent.js
โ โ โโโ FoodAgent.js
โ โ โโโ ItineraryAgent.js
โ โโโ core/
โ โ โโโ AgentOrchestrator.js # Real-time 3-phase coordinator
โ โ โโโ PlannerOrchestrator.js # (legacy offline orchestrator)
โ โ โโโ config.js
โ โ โโโ constants.js
โ โโโ mcp/
โ โ โโโ mcpServer.js # MCP JSON-RPC 2.0 server (Express)
โ โ โโโ mcpClient.js # MCP client with convenience wrappers
โ โ โโโ startServer.js # Standalone server entry point
โ โโโ realtime/
โ โ โโโ serperClient.js # Google Serper API wrapper
โ โโโ models/
โ โ โโโ TravelPlan.js # Shared data model
โ โโโ ui/
โ โ โโโ realtimeApp.js # Real-time app loop
โ โ โโโ realtimeDisplay.js # Terminal rendering (live-aware)
โ โ โโโ realtimePrompts.js # Inquirer prompts
โ โ โโโ app.js # (legacy UI)
โ โ โโโ display.js
โ โ โโโ prompts.js
โ โโโ data/
โ โ โโโ destinationData.js # Curated city data (fallback)
โ โ โโโ visaRules.js
โ โโโ utils/
โ โโโ logger.js
โ โโโ helpers.js
โ โโโ openaiClient.js
โ โโโ geoClient.js
โ โโโ weatherClient.js
โโโ scripts/
โ โโโ verify.js # End-to-end test suite
โโโ plans/ # Saved JSON trip plans (auto-created)
โโโ .env.example
โโโ package.json
โโโ README.mdโ What's Live vs Estimated
Feature | With Serper key | Without Serper key |
Flight prices | โ Live Google search | โก Distance-based estimate |
Hotel prices & names | โ Live + ratings | โก Tier-based estimate |
Attractions | โ Live places + ratings | โก Built-in city data |
Weather | โ Live forecast | โก Open-Meteo API (free) |
Visa info | โ Live Google search | โก Local rules database |
Restaurant names | โ Live places | โก Built-in city data |
Safety info | โ Live advisories | โก Local curated data |
Daily cost estimates | โ Live cost pages | โก Tier-based defaults |
Itinerary | โ AI+live places / rule-based+live | โก Rule-based built-in |
๐ Requirements
Node.js 18+
npm
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Travel tools for AI agents: plan and edit real trips, search stays and tours, import travel videos.
Aggregated travel MCP โ flights, tours, activities, price checks, visas, and more.
Personal AI travel agent. Points optimization, live flight/hotel/award search, trip planning.
Search and compare flight offers through a cache-aware Streamable HTTP MCP server for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceProvides weather-aware travel planning tools that fetch 3-day forecasts and generate structured itineraries using a multi-agent orchestration system. It exposes specialized agents for weather data and trip planning to any MCP-compliant client.-
- AlicenseAqualityBmaintenanceEnables AI agents to plan trips by searching flights, accommodations, and activities, and managing itineraries collaboratively with role-based permissions.2001MIT
- FlicenseNot gradedqualityBmaintenanceEnables managing travel itineraries with CRUD tools for journeys, stops, and plan items, plus weather lookup, integrated with public MCP servers for time and web search.-
- AlicenseNot gradedqualityCmaintenanceCoordinates flights, hotels, events, weather, currency, and traffic data through a single MCP server, enabling comprehensive trip planning via natural language prompts.MIT