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., "@Travel MCP Server Find flights from NYC to Tokyo for next week and estimate a mid-range budget for 2 people."
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.
A Model Context Protocol (MCP) server for comprehensive travel planning, providing flight search, accommodation booking, currency exchange, weather forecasting, and trip budget calculation capabilities.
š« Flight Search: Find and compare flights with various options
šØ Accommodation Search: Search for hotels, vacation rentals, and other accommodations
š± Currency Exchange: Get real-time exchange rates for travel budgeting
š¤ļø Weather Forecast: Check weather conditions for your travel dates
š° Trip Budget Calculator: Calculate and plan your travel expenses
Related MCP server: Ingrids Reisetjenester
Clone the repository:
git clone <repository-url>
cd travel-mcp-serverInstall dependencies:
npm installSet up environment variables:
Copy .env.example to .env
Fill in your API keys (see API Keys Setup)
You'll need to obtain API keys from the following services:
Flight API: Amadeus, Skyscanner, or similar flight data provider
Accommodation API: Booking.com, Airbnb, or similar accommodation service
Currency Exchange API: Fixer.io, ExchangeRate-API, or similar service
Weather API: OpenWeatherMap, WeatherAPI, or similar weather service
Google Places API: For attractions and restaurant recommendations
Update your .env file with these keys:
FLIGHT_API_KEY=your_flight_api_key
BOOKING_API_KEY=your_booking_api_key
EXCHANGE_API_KEY=your_exchange_api_key
WEATHER_API_KEY=your_weather_api_key
GOOGLE_PLACES_API_KEY=your_google_places_api_keyRun the server in development mode with hot reload:
npm run devBuild and start the server:
npm run build
npm startRun with automatic restart on file changes:
npm run watchThe MCP server provides the following tools:
search_flights)Search for flights between destinations with customizable options.
Parameters:
origin: Departure airport/city
destination: Arrival airport/city
departureDate: Departure date
returnDate: Return date (optional for one-way)
passengers: Number of passengers
class: Flight class (economy, business, first)
search_accommodation)Find hotels, vacation rentals, and other accommodation options.
Parameters:
destination: City or location
checkIn: Check-in date
checkOut: Check-out date
guests: Number of guests
rooms: Number of rooms
type: Accommodation type (hotel, apartment, etc.)
get_exchange_rate)Get current exchange rates between currencies.
Parameters:
from: Source currency code (e.g., USD)
to: Target currency code (e.g., EUR)
amount: Amount to convert (optional)
get_weather_forecast)Check weather conditions for your travel destination.
Parameters:
location: City or location
date: Date for forecast
days: Number of days to forecast (optional)
calculate_trip_budget)Calculate estimated trip costs including flights, accommodation, and daily expenses.
Parameters:
destination: Travel destination
duration: Trip duration in days
travelers: Number of travelers
category: Budget category (budget, mid-range, luxury)
travel-mcp-server/
āāā src/
ā āāā index.ts # Main server entry point
ā āāā services/
ā āāā FlightService.ts # Flight search functionality
ā āāā AccommodationService.ts # Accommodation search
ā āāā CurrencyService.ts # Currency exchange
ā āāā WeatherService.ts # Weather forecasting
āāā dist/ # Compiled TypeScript output
āāā package.json # Project dependencies and scripts
āāā tsconfig.json # TypeScript configuration
āāā .env # Environment variables (not in repo)
āāā .gitignore # Git ignore rules
āāā README.md # This fileThis server can be used with any MCP-compatible client such as:
Claude Desktop
Other AI assistants supporting MCP
Custom MCP client applications
Add the server to your MCP client configuration:
{
"mcpServers": {
"travel-planner": {
"command": "npx",
"args": ["travel-mcp-server"]
}
}
}TypeScript: Type-safe JavaScript development
Node.js: Runtime environment
MCP SDK: Model Context Protocol implementation
Axios: HTTP client for API requests
Zod: Schema validation
dotenv: Environment variable management
Create a new service class in src/services/
Implement the required methods
Register the service in src/index.ts
Add corresponding tools and handlers
npm testFork the repository
Create a feature branch: git checkout -b feature-name
Make your changes
Run tests: npm test
Commit your changes: git commit -m 'Add feature'
Push to the branch: git push origin feature-name
Submit a pull request
This project is licensed under the ISC License - see the LICENSE file for details.
If you encounter any issues or have questions:
Check the Issues section
Create a new issue with detailed information
Provide logs and reproduction steps
Add more travel service integrations
Implement caching for API responses
Add travel itinerary planning
Support for group travel coordination
Integration with calendar services
Mobile app companion
Note: Remember to keep your API keys secure and never commit them to version control. Always use environment variables for sensitive configuration.
Calculate total estimated budget for a trip
| Name | Required | Description | Default |
|---|---|---|---|
| duration | Yes | Trip duration in days | |
| travelers | No | Number of travelers | |
| budgetLevel | Yes | Budget level preference | |
| destinations | Yes | List of destination cities |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for disclosing behavioral traits. It only states 'Calculate total estimated budget' without indicating side effects, required permissions, or whether it is a read-only operation. No mention of data sources or accuracy.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately communicates the tool's purpose. It is efficient with no wasted words. Could be slightly more informative while maintaining brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fails to explain what the output looks like, as there is no output schema. It does not specify whether the budget includes breakdowns, currency, or assumptions. For a tool that computes a value, this is a significant gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All four parameters are described in the input schema (100% coverage). The description adds no additional meaning beyond what the schema provides. It does not clarify relationships between parameters or provide examples of valid inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: calculating a total estimated budget for a trip. It is distinct from sibling tools (exchange rate, weather, accommodation, flights) which cover different aspects of trip planning. However, it could be more specific about what factors into the budget (e.g., based on destinations, duration, budget level).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus siblings. However, the sibling tools are clearly in different domains (exchange rates, weather, accommodation, flights), so usage context is implied. The description lacks when-not or alternative recommendations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current currency exchange rates
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Target currency code (e.g., EUR) | |
| from | Yes | Source currency code (e.g., USD) | |
| amount | No | Amount to convert |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description does not disclose behavioral traits like data freshness, authentication needs, or rate limits. It only states the basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, front-loaded sentence that conveys the core purpose without any wasted words. Appropriate length for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should indicate what the tool returns (e.g., rate or converted amount), but it does not. The description is incomplete for agent decision-making.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with parameter descriptions, but the tool description adds no additional meaning or context beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'current currency exchange rates', which is specific and distinguishes it from sibling tools like calculate_trip_budget or search_accommodation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., calculate_trip_budget might also involve conversions). No explicit when-not or context for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get weather forecast for travel dates
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | City name | |
| country | Yes | Country name | |
| endDate | Yes | End date (YYYY-MM-DD) | |
| startDate | Yes | Start date (YYYY-MM-DD) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must carry full burden. It only states 'Get weather forecast for travel dates', omitting details like forecast period units, data source, or whether it is forecast or historical. Minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded, no unnecessary words. Efficient and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite simple parameters, no output schema or annotations means the description should compensate with more context (e.g., return format, temperature units, daily vs hourly). Missing details for a complete understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all parameters have descriptions. The description adds no extra meaning beyond the schema, but the baseline is 3 for full coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets weather forecasts for travel dates using a specific verb ('Get') and resource ('weather forecast'). It is distinct from sibling tools which cover budget, exchange, accommodation, and flights, so no confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. Sibling tools are clearly different (budget, exchange, accommodation, flights), so usage is implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for hotels and accommodations
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | City name | |
| budget | No | Maximum budget per night in USD | |
| guests | No | Number of guests | |
| checkIn | Yes | Check-in date (YYYY-MM-DD) | |
| checkOut | Yes | Check-out date (YYYY-MM-DD) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It does not mention that the tool is read-only, what the output format is, or any side effects. This is insufficient for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no wasted words. It is appropriately brief but could be more informative without sacrificing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lacks context about the tool's behavior, return values, and constraints (e.g., required parameters). Given no output schema, a more complete description is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides for parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search for hotels and accommodations,' which clearly identifies the verb and resource. However, it lacks explicit differentiation from sibling tools, though the sibling tools are in different domains (budget, exchange rate, weather, flights).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description offers no context about prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for flight prices and schedules
| Name | Required | Description | Default |
|---|---|---|---|
| origin | Yes | Origin city/airport code | |
| departDate | Yes | Departure date (YYYY-MM-DD) | |
| passengers | No | Number of passengers | |
| returnDate | No | Return date (YYYY-MM-DD) | |
| destination | Yes | Destination city/airport code |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only says 'search for flight prices and schedules'. It does not disclose any behavioral traits such as whether results are real-time, caching behavior, data sources, or limitations, which leaves the agent uninformed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and to the point, with no wasted words. It earns its place by stating the core purpose, though it could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of flight search (5 parameters, no output schema, no annotations), the description is insufficient. It does not explain the return format, round-trip behavior, or any constraints, leaving significant gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers all parameters with descriptions (100% coverage). The description adds no additional meaning beyond what is already in the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for flight prices and schedules, with a specific verb and resource. While it does not explicitly distinguish from siblings, the siblings are different travel tools, making the purpose sufficiently clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description lacks context about scenarios where flight search is appropriate or when to consider other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct aspect of travel planning: budget, exchange rates, weather, accommodation, and flights. There is no overlap in purpose, making it easy for an agent to select the correct tool.
All tool names follow a consistent verb_noun pattern (e.g., calculate_trip_budget, search_flights), with the verb describing the action and the noun the entity, ensuring predictability.
With 5 tools, the server is well-scoped for a travel planning assistant, covering the essential tasks without being too sparse or overwhelming.
The set covers core travel planning needs (budget, exchange, weather, flights, accommodation), leaving only minor gaps such as destination information or itinerary management, which agents can work around.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Your personal AI travel concierge ā flights, hotels, 116M+ POIs, visas, weather & more
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Plan your financial future with AI: track net worth, manage budgets, and forecast scenarios.
Personal AI travel agent. Points optimization, live flight/hotel/award search, trip planning.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gs-ysingh/travel-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
