Kiwi.com Flight Search
The Kiwi.com Flight Search MCP Server connects your AI assistant directly to Kiwi.com’s flight search engine.
The MCP server allows your AI to search for and book flights based on your specific travel requirements.
You can use it through Claude, Cursor, or other MCP-compatible clients to find flight options without switching applications.
Features
- ✈️ Search for one-way or round-trip flights
- 🌍 Find flights by city or airport codes
- 📅 Specify exact travel dates or use +/- 3 day flexibility
- 👨👩👧👦 Set passenger counts (adults, children, infants)
- 🛋️ Select cabin class (economy to first class)
- 🔗 Get direct booking links for selected flights
Use Cases
- Quick Vacation Planning: You’re thinking about a family trip. You can ask your AI, “Find round-trip flights for two adults and two kids from Vienna to London from August 3rd to 10th.” The server will return a list of suitable options with booking links.
- Last-Minute Business Travel: A sudden meeting comes up. You can tell your assistant, “I need a first-class, one-way ticket from Paris to Rome for tomorrow,” and get immediate results.
- Comparing Flexible Dates: If your travel dates aren’t fixed, you can check for better prices. For instance, ask, “Find the best price for a flight from New York to Lisbon next month with flexible dates.”
- Developer Integration Testing: If you’re building a custom AI agent, you can use this server to test and integrate flight search functionalities into your application without needing to build the backend logic yourself.
Installation
Cursor
{
"mcpServers": {
"kiwi-com-flight-search": {
"url": "https://mcp.kiwi.com"
}
}
}Claude Desktop
{
"mcpServers": {
"kiwi-com-flight-search": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.kiwi.com"
]
}
}
}Claude Code
claude mcp add --transport http kiwi-com-flight-search https://mcp.kiwi.com
Usage
After installing the server through your preferred MCP client, you interact with it through natural language queries. The server exposes a single tool called search-flight that handles all flight search parameters.
The search-flight tool accepts these parameters:
- trip_type: “one-way” or “round-trip”
- origin: City name or airport code
- destination: City name or airport code
- departure_date: Date in YYYY-MM-DD format
- return_date: Required for round-trip flights
- adults: Number of adult passengers
- children: Number of child passengers
- infants: Number of infant passengers
- cabin_class: “economy”, “premium_economy”, “business”, or “first”
- flexibility: true/false for +/- 3 day date flexibility
You don’t need to manually construct these parameters. Instead, ask your AI assistant natural questions like “Find me business class flights from New York to London next Tuesday for two adults” or “Show economy flights from Paris to Tokyo with flexible dates in September.”
The AI will parse your request, call the search-flight tool with the appropriate parameters, and present you with flight options that include prices, airlines, times, and direct booking links.
FAQs
Q: Can I complete the entire booking process inside my AI assistant?
A: Not at this time. The server provides a direct link to the Kiwi.com website to complete your booking securely.
Q: Does this tool support multi-city flight searches?
A: The current version focuses on one-way and round-trip searches.
Q: Do I need a Kiwi.com API key to use this MCP server?
A: No, an API key is not required. The server is configured to work directly with the provided URL.
Latest MCP Servers
CVE
WebMCP
webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…
Google Meta Ads GA4
Featured MCP Servers
Notion
Claude Peers
Excalidraw
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.



