Frequently Asked Questions (FAQ) - Flight + Stay Search MCP Server
Q: What is an MCP Server? A: MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to Large Language Models (LLMs).
Q: What is the Flight + Stay Search MCP Server? A: It’s a TypeScript implementation that uses the Duffel API to search for flights (one-way, round-trip, multi-city) and accommodations. It’s designed to integrate with AI Agents for automated travel planning.
Q: What is the Duffel API? A: Duffel provides a comprehensive suite of tools for airlines and travel providers, offering access to flight data and services.
Q: What types of flights can I search for with this MCP Server? A: You can search for one-way, round-trip, and multi-city flights.
Q: What kind of information can I get about flight offers? A: You can get detailed information about flight times, layovers, included amenities, and more.
Q: Can I filter flight searches by cabin class or number of passengers? A: Yes, you can specify preferences such as cabin class, the number of passengers, and connection preferences.
Q: Can I search for hotels and accommodations with this MCP Server? A: Yes, the server includes functionality to search for travel stays, including hotels and other accommodations.
Q: How can I access guest reviews for hotels? A: The server provides access to guest reviews for hotels and stays, allowing users to make informed decisions.
Q: What are the key features of the search_stays tool?
A: The search_stays tool allows you to search for accommodations by location, check-in date, check-out date, number of guests, and other criteria.
Q: What are the parameters for the search_stays tool?
A: The parameters include location, check_in_date, check_out_date, guests, rooms (optional), and radius_km (optional).
Q: How do I get guest reviews for a specific hotel?
A: Use the get_stay_reviews tool with the stay_id of the hotel.
Q: What parameters does the get_stay_reviews tool require?
A: The required parameter is stay_id. Optional parameters include after, before, and limit for pagination and limiting the number of reviews returned.
Q: How do I install the Flight + Stay Search MCP Server?
A: Use npm install to install the dependencies.
Q: How do I run the Flight + Stay Search MCP Server?
A: After installing dependencies, build the project with npm run build and then start the server with npm start.
Q: What environment variables do I need to set?
A: You need to set the DUFFEL_API_KEY environment variable with your Duffel API key.
Q: Can I use a test API key for development?
A: Yes, you can use a test API key (duffel_test) to try the functionality.
Q: What is UBOS? A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department.
Q: How does UBOS help with AI Agent development? A: UBOS helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.
Q: How do I integrate this MCP server with UBOS?
A: You can publish the MCP to Smithery (part of the UBOS ecosystem) using npx @smithery/cli publish and then run it with npx @smithery/cli run @your-username/flights-mcp-ts --config '{"duffelApiKey":"your_duffel_api_key"}'.
Q: What license is the Flight + Stay Search MCP Server released under? A: The server is released under the MIT License.
Flight & Stay Search Server (Duffel API)
Project Details
- clockworked247/flights-mcp-ts
- Last Updated: 4/17/2025
Recomended MCP Servers
GitLabのカンバンボード操作を行うためのMCPサーバー
An MCP server to help you "play with your documents" via Docling 🐥
dameng-mcp-server
Model Context Protocol (MCP) Server for HashiCorp Vault secret management
This read-only MCP Server allows you to connect to Microsoft Teams data from Claude Desktop through CData JDBC...
GitHub's official MCP Server
daily.dev is a professional network for developers to learn, collaborate, and grow together 👩🏽💻 👨💻
A really simple MCP server for Jira, which uses docker for easy deployment.





