Flighty MCP

Flighty MCP

Enables AI assistants to access and manage your Flighty flight data directly from the local macOS app database, supporting flight lists, status, searches, additions, and more.

Category
访问服务器

README

Flighty MCP

A local MCP (Model Context Protocol) server that gives AI assistants access to your Flighty flight data. Reads directly from the Flighty macOS app's local SQLite database.

Features

  • List your flights - View your own upcoming, past, or all flights
  • List friends' flights - View connected friends' flights, filterable by name
  • Get flight details - Look up any flight by number or ID
  • Search flights - Filter by airline, airport, date range
  • Flight status - Check current status, delays, gates, weather
  • Delay forecast - Historical on-time performance statistics
  • Add flights - Add a flight by flight code and date, with optional auto-lookup of airports
  • Airport search - Look up airports by IATA code, city, or name
  • Airline search - Look up airlines by IATA code, name, or alliance
  • Flight stats - Aggregate statistics (distance, top routes, airlines)
  • Connections - View layovers and connection times

Prerequisites

  • macOS with the Flighty app installed
  • Python 3.11+
  • uv package manager
  • (Optional) Free AirLabs API key for automatic airport lookup when adding flights

Setup

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "flighty": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/flighty-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

To enable automatic airport lookup when adding flights, add your AirLabs API key:

{
  "mcpServers": {
    "flighty": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/flighty-mcp",
        "run",
        "main.py"
      ],
      "env": {
        "AIRLABS_API_KEY": "your-api-key-here"
      }
    }
  }
}

You can get a free API key at airlabs.co.

Claude Code

claude mcp add flighty -- uv --directory /path/to/flighty-mcp run main.py

With AirLabs API key:

claude mcp add flighty -e AIRLABS_API_KEY=your-api-key-here -- uv --directory /path/to/flighty-mcp run main.py

Configuration

By default, the server reads from:

~/Library/Containers/com.flightyapp.flighty/Data/Documents/MainFlightyDatabase.db

Override with the FLIGHTY_DB_PATH environment variable if needed.

Environment Variables

Variable Required Description
FLIGHTY_DB_PATH No Override the default Flighty database path
AIRLABS_API_KEY No AirLabs API key for automatic airport lookup when adding flights. Without this, you must provide departure and arrival airports manually.

Tools

Tool Description
list_flights List your own flights with filters (upcoming/past/archived)
list_friend_flights List connected friends' flights, optionally filtered by name
get_flight Get detailed flight info by ID or flight number
search_flights Search by airline, airports, date range
get_flight_status Current status, delays, gates, weather
get_delay_forecast Historical delay statistics
add_flight Add a flight by code and date (airports auto-resolved with AirLabs API key)
search_airports Search airports by code, city, or name
search_airlines Search airlines by code, name, or alliance
get_flight_stats Aggregate stats (distance, top routes, etc.)
get_connections Flight connections and layover info

Example Queries

  • "What are my upcoming flights?"
  • "What flights does Felix have coming up?"
  • "How often is UA194 delayed?"
  • "Add flight LH400 on 2026-04-15"
  • "Show my flight stats for 2025"
  • "What gate does my next flight depart from?"
  • "Search for airports in Tokyo"

License

MIT

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