Ferryhopper MCP Server
The Ferryhopper MCP Server exposes ferry routes, schedules and booking redirects so an AI assistant can discover connections across Europe and the Mediterranean and send users to Ferryhopper to complete bookings.
Overview
The Ferryhopper MCP Server exposes ferry routes, schedules and booking redirects so an AI assistant can discover connections across Europe and the Mediterranean and send users to Ferryhopper to complete bookings.
An MCP app (see the official overview) is any client that can consume remote MCP tools and optionally render UI artifacts they return. Whether you run Claude Desktop, Cursor, Gemini, VS Code, or a custom agent, pointing it at this server instantly upgrades it with Ferryhopper ferry-search skills.
Key features
- 🌍Search ports and connections across 33 countries and 190+ ferry operators
- ⛴️Get real-time ferry itineraries with indicative prices
- đź”—Receive a direct link to Ferryhopper.com for booking and payment
Use cases
- Assist users searching for ferry routes and daily itineraries
- Recommend destinations based on departure port and date
- Power travel chatbots to plan island-hopping or multi-leg journeys
Client integration options
- 📱MCP-ready hosts consume our toolset and, if they support iframe-style MCP apps, render the bundled UI resource (Trips Carousel) exactly as designed.
- đź§©Text-only or command-line clients use the same tools endpoint, simply ignoring the UI resource and working with the structured JSON responses for ports, trips, and connections.
UI resources
Beyond the tools, we expose a resource named search-trips-carousel at ui://widgets/trips-carousel.html. Hosts fetch it to embed our Trips Carousel HTML (served as text/html;profile=mcp-app) along with CSP hints, so iframe-capable MCP environments can paint the exact UI we ship.
Available Tools
Get ports
{
"name": "get_ports",
"description": "Get a list of global ports and their details"
}
Search trips
This is the engine behind our Trips Carousel UI: hosts that support MCP app surfaces can render the provided cards, while purely conversational hosts consume the same structured JSON payload (operators, prices, ETAs) without rendering.
{
"name": "search_trips",
"description": "Return carousel-ready UI blocks plus identical structured data for hosts without MCP app rendering",
"parameters": {
"departureLocation": "string",
"arrivalLocation": "string",
"date": "string (YYYY-MM-DD)"
}
}
Get Direct Connections
{
"name": "",
"description": "Get a list of all the direct connections between ports",
"parameters": {
"portLocation": "string"
}
}
Installation & Setup
The MCP clients directory lists the current set of supported apps and agents that can connect to MCP servers, so teams with MCP-enabled clients can hook into Ferryhopper immediately. You can also connect from any custom MCP client if you are building your own app, and organizations without an app implementation can still use the same remote endpoint through lightweight CLI runners or hosted connectors—no custom UI required. Application Examples:
- Gemini CLI
- ChatGPT
- Claude.ai / Claude Desktop Consult their documentation and use the following URL for connecting:
https://mcp.ferryhopper.com/mcp
Example Prompts
“What ferries depart from Piraeus to Aegina on Saturday morning?”
“Help me find a ferry from Ibiza to Barcelona on July 11th.”
“I want to visit an island within 3 hours of Athens tomorrow and return the next day, what are my options?”
Related Servers
NPMLens MCP
NPMLens MCP lets your coding agent (such as Claude, Cursor, Copilot, Gemini or Codex) search the npm registry and fetch package context (README, downloads, GitHub info, usage snippets). It acts as a Model‑Context‑Protocol (MCP) server, giving your AI assistant a structured way to discover libraries and integrate them quickly.
Wikimedia Image Search
MCP server that enables AI assistants to search Wikimedia Commons images with metadata and visual thumbnails.
Unreal Engine Knowledge Graph
Search concept relationships in the Unreal Engine official documentation using a Neo4j-powered knowledge graph.
Search1API
One API for Search, Crawling, and Sitemaps
Google Search
Perform Google searches and view web content with advanced bot detection avoidance.
Caltrain MCP Server
Provides real-time Caltrain schedule information using GTFS data.
Unified Search MCP Server
Provides unified search capabilities across Google Scholar, Google Web Search, and YouTube.
DeepResearch
Lightning-Fast, High-Accuracy Deep Research Agent 👉 8–10x faster 👉 Greater depth & accuracy 👉 Unlimited parallel runs
Qdrant Retrieve
Semantic search using the Qdrant vector database.
Wikipedia
Retrieves information from Wikipedia to provide context to Large Language Models (LLMs).