CruiseFeed

CruiseFeed

Query cruise sailings, fares, price drops & ship specs

Category
访问服务器

README

CruiseFeed MCP server

A remote Model Context Protocol server that exposes the live CruiseFeed API (https://api.cruisefeed.io) as tools, so AI agents (Claude, and any MCP-capable app) can search cruises, pull itineraries and fares, track price drops, and read ship specs directly.

It runs as a Cloudflare Worker (Streamable HTTP transport) and is a thin, faithful wrapper: every tool maps to a real GET endpoint on the live API — nothing is invented.

Tools

Tool Wraps Purpose
search_cruises GET /v1/cruises filter sailings by line, ship, port, region, dates, price, nights, round-trip
get_cruise GET /v1/cruises/{id} full sailing: itinerary, per-cabin fares, taxes, matched ship
get_cruise_price_history GET /v1/cruises/{id}/history daily price timeline (change days only)
list_price_changes GET /v1/changes recent fare moves — the price-drop feed
search_ships GET /v1/ships vessels by name / operator / flag state, with specs
get_ship GET /v1/ships/{id} one ship's full spec sheet (by IMO)
list_cruise_lines GET /v1/cruise-lines reference facet
list_ports GET /v1/ports reference facet
get_stats GET /v1/stats catalogue size + freshness

Authentication

Each caller supplies their own CruiseFeed API key (get one at https://cruisefeed.io). The server reads it, in order of preference, from:

  1. the X-CruiseFeed-Key request header (recommended), or
  2. Authorization: Bearer <key>, or
  3. the Worker's own CRUISEFEED_API_KEY secret (single-tenant / demo fallback).

The key is forwarded to the API as Authorization: Bearer; the API enforces the plan's monthly quota and rate limits. The server stores nothing.

Develop & test locally

cd cruisefeed-mcp
npm install
# .dev.vars holds a CRUISEFEED_API_KEY for local runs (gitignored). Create it if missing:
#   echo "CRUISEFEED_API_KEY=cf_live_..." > .dev.vars
npm run dev          # wrangler dev -> http://localhost:8787/mcp

Inspect the tools with the MCP Inspector:

npx @modelcontextprotocol/inspector@latest
# then connect to http://localhost:8787/mcp (Streamable HTTP)

Deploy (Cloudflare)

Live at https://mcp.cruisefeed.io/mcp.

npx wrangler login       # one-time (if not already authenticated)
npm run deploy           # -> https://mcp.cruisefeed.io/mcp

No CRUISEFEED_API_KEY secret is set in production — the server is purely bring-your-own-key: every caller must send their own key, and keyless calls return 401. (The env-key fallback in the code only activates if you choose to wrangler secret put CRUISEFEED_API_KEY for a private, single-tenant instance.) To move it to a custom domain like mcp.cruisefeed.io, add a Worker route.

Connect from Claude

Add the live URL as a remote MCP server and set your CruiseFeed key as a header:

{
  "mcpServers": {
    "cruisefeed": {
      "url": "https://mcp.cruisefeed.io/mcp",
      "headers": { "X-CruiseFeed-Key": "cf_live_your_key" }
    }
  }
}

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选